HOLYCORES
中文Contact →
PRODUCTSHELIOSSPARKNOVAAETHER
SoftwareLaboratorySolutionsAsk HolycoresDevelopersCompanyCareersContact
中文

CAREERS / 17 OPEN ROLES

Explore every open role,
in one place.

Choose the problem you want to solve across silicon, systems, software, and product.
ROLE DIRECTORY
Advanced Packaging Process EngineerAI/ML Physical Design Flow EngineerChiplet Design ArchitectGCC Compiler EngineerMachine Learning Research Engineer (LLMs & AI Systems)Physical Design Engineer, PnRPower ArchitectPrincipal CPU Microarchitect - RISC-V & AI ComputeProduct Manager - Hardware SystemsSenior Embedded Engineer, AI IPSoftware Engineer, Acceleration Kernel DevelopmentSoftware Engineer, AI CompilerSoftware Engineer-AI Model Bring UpSoftware Engineer, Metal Runtime (Core Systems)Software Engineer, Scale OutSr Engineer, AI KernelTechnical Program Manager, Product Software
ENGLISH ROLE DETAILS

17 open roles

01

Advanced Packaging Process Engineer

Shanghai, China

Apply now →

About the role

Own critical engineering work that turns advanced AI silicon constraints into a manufacturable design while balancing performance, power, area, reliability, and production risk.

What you will do

  • Build and maintain implementation, analysis, or packaging flows for advanced process technology
  • Partner with architecture, RTL, verification, DFT, packaging, and manufacturing teams
  • Diagnose timing, power, signal-integrity, thermal, or yield issues and drive closure
  • Improve flow quality and repeatability through automation, metrics, and reviews

What we look for

  • Background in electrical engineering, microelectronics, computer engineering, or a related field
  • Depth in at least one semiconductor implementation, signoff, or advanced packaging discipline
  • Ability to improve engineering workflows with scripting and data analysis
  • Strong cross-functional communication and end-to-end ownership

How we work

We value first-principles reasoning, direct communication, measurable engineering evidence, and collaboration across silicon, systems, software, and customer workloads.

02

AI/ML Physical Design Flow Engineer

Shanghai, China

Apply now →

About the role

Own critical engineering work that turns advanced AI silicon constraints into a manufacturable design while balancing performance, power, area, reliability, and production risk.

What you will do

  • Build and maintain implementation, analysis, or packaging flows for advanced process technology
  • Partner with architecture, RTL, verification, DFT, packaging, and manufacturing teams
  • Diagnose timing, power, signal-integrity, thermal, or yield issues and drive closure
  • Improve flow quality and repeatability through automation, metrics, and reviews

What we look for

  • Background in electrical engineering, microelectronics, computer engineering, or a related field
  • Depth in at least one semiconductor implementation, signoff, or advanced packaging discipline
  • Ability to improve engineering workflows with scripting and data analysis
  • Strong cross-functional communication and end-to-end ownership

How we work

We value first-principles reasoning, direct communication, measurable engineering evidence, and collaboration across silicon, systems, software, and customer workloads.

03

Chiplet Design Architect

Shanghai, China

Apply now →

About the role

Define next-generation AI compute and RISC-V architecture by translating workloads into decisions across compute, memory, interconnect, power, and software programmability.

What you will do

  • Analyze representative AI and systems workloads and build performance models
  • Define microarchitecture, dataflow, memory hierarchy, interconnect, or power goals
  • Evaluate tradeoffs with RTL, compiler, kernel, systems, and verification teams
  • Calibrate architectural assumptions with models, prototypes, and silicon data

What we look for

  • Background in computer architecture, electrical engineering, or a related field
  • Understanding of CPU, NPU, GPU, or high-performance interconnect design
  • Experience in performance modeling, workload analysis, or microarchitecture
  • Ability to communicate complex tradeoffs and drive cross-layer decisions

How we work

We value first-principles reasoning, direct communication, measurable engineering evidence, and collaboration across silicon, systems, software, and customer workloads.

04

GCC Compiler Engineer

Shanghai, China

Apply now →

About the role

Build the compiler toolchain that connects mainstream models to HOLYCORES hardware, improving correctness, performance, and developer experience through graph optimization and code generation.

What you will do

  • Design compiler frontends, intermediate representations, optimizations, and code generation
  • Enable new operators, data types, dynamic shapes, and hardware capabilities
  • Analyze compilation quality and runtime performance across the stack
  • Build automated tests, regression infrastructure, debugging tools, and documentation

What we look for

  • Background in computer science, compilers, or a related discipline
  • Strong C/C++ and knowledge of compiler IR or code generation
  • Experience with GCC, LLVM, MLIR, or an AI compiler framework
  • Commitment to software quality, interface design, and reproducible performance

How we work

We value first-principles reasoning, direct communication, measurable engineering evidence, and collaboration across silicon, systems, software, and customer workloads.

05

Machine Learning Research Engineer (LLMs & AI Systems)

Shanghai, China

Apply now →

About the role

Bring real AI models onto HOLYCORES platforms with correct and efficient execution across research, operators, compilers, kernels, and system performance.

What you will do

  • Port and validate language, vision, or multimodal models
  • Analyze operator coverage, numerical accuracy, memory, and performance
  • Optimize critical paths with compiler and kernel engineers
  • Create model baselines, automated regression, and reproducible benchmarks

What we look for

  • Experience with PyTorch and modern AI model architectures
  • Strong Python with C++ capability for performance-critical work
  • Understanding of numerical accuracy and training or inference tradeoffs
  • Data-driven cross-layer performance engineering

How we work

We value first-principles reasoning, direct communication, measurable engineering evidence, and collaboration across silicon, systems, software, and customer workloads.

06

Physical Design Engineer, PnR

Shanghai, China

Apply now →

About the role

Own critical engineering work that turns advanced AI silicon constraints into a manufacturable design while balancing performance, power, area, reliability, and production risk.

What you will do

  • Build and maintain implementation, analysis, or packaging flows for advanced process technology
  • Partner with architecture, RTL, verification, DFT, packaging, and manufacturing teams
  • Diagnose timing, power, signal-integrity, thermal, or yield issues and drive closure
  • Improve flow quality and repeatability through automation, metrics, and reviews

What we look for

  • Background in electrical engineering, microelectronics, computer engineering, or a related field
  • Depth in at least one semiconductor implementation, signoff, or advanced packaging discipline
  • Ability to improve engineering workflows with scripting and data analysis
  • Strong cross-functional communication and end-to-end ownership

How we work

We value first-principles reasoning, direct communication, measurable engineering evidence, and collaboration across silicon, systems, software, and customer workloads.

07

Power Architect

Shanghai, China

Apply now →

About the role

Define next-generation AI compute and RISC-V architecture by translating workloads into decisions across compute, memory, interconnect, power, and software programmability.

What you will do

  • Analyze representative AI and systems workloads and build performance models
  • Define microarchitecture, dataflow, memory hierarchy, interconnect, or power goals
  • Evaluate tradeoffs with RTL, compiler, kernel, systems, and verification teams
  • Calibrate architectural assumptions with models, prototypes, and silicon data

What we look for

  • Background in computer architecture, electrical engineering, or a related field
  • Understanding of CPU, NPU, GPU, or high-performance interconnect design
  • Experience in performance modeling, workload analysis, or microarchitecture
  • Ability to communicate complex tradeoffs and drive cross-layer decisions

How we work

We value first-principles reasoning, direct communication, measurable engineering evidence, and collaboration across silicon, systems, software, and customer workloads.

08

Principal CPU Microarchitect - RISC-V & AI Compute

Shanghai, China

Apply now →

About the role

Define next-generation AI compute and RISC-V architecture by translating workloads into decisions across compute, memory, interconnect, power, and software programmability.

What you will do

  • Analyze representative AI and systems workloads and build performance models
  • Define microarchitecture, dataflow, memory hierarchy, interconnect, or power goals
  • Evaluate tradeoffs with RTL, compiler, kernel, systems, and verification teams
  • Calibrate architectural assumptions with models, prototypes, and silicon data

What we look for

  • Background in computer architecture, electrical engineering, or a related field
  • Understanding of CPU, NPU, GPU, or high-performance interconnect design
  • Experience in performance modeling, workload analysis, or microarchitecture
  • Ability to communicate complex tradeoffs and drive cross-layer decisions

How we work

We value first-principles reasoning, direct communication, measurable engineering evidence, and collaboration across silicon, systems, software, and customer workloads.

09

Product Manager - Hardware Systems

Shanghai, China

Apply now →

About the role

Connect customer workloads, product direction, and engineering execution by turning complex technology into clear requirements, milestones, decisions, and deliverables.

What you will do

  • Synthesize customer, developer, and internal requirements
  • Define product boundaries, priorities, roadmaps, and success metrics
  • Drive milestone-based collaboration across hardware, software, systems, and business teams
  • Surface risks, dependencies, and decisions through clear communication

What we look for

  • Experience in semiconductors, AI infrastructure, or systems software
  • Ability to understand complex technology and form product judgment
  • Strong program execution, cross-functional coordination, and writing
  • Focus on customer outcomes and reusable platform capabilities

How we work

We value first-principles reasoning, direct communication, measurable engineering evidence, and collaboration across silicon, systems, software, and customer workloads.

10

Senior Embedded Engineer, AI IP

Shanghai, China

Apply now →

About the role

Develop low-level software for AI IP and systems, connecting boot, firmware, drivers, device management, and runtime for reliable bring-up and production deployment.

What you will do

  • Implement firmware, drivers, boot, and device-control capabilities
  • Support new-silicon and board bring-up, debugging, and validation
  • Build diagnostics, telemetry, update, recovery, and security mechanisms
  • Resolve issues across hardware, verification, runtime, and systems teams

What we look for

  • Strong C/C++ and embedded debugging skills
  • Knowledge of SoCs, buses, interrupts, DMA, memory, and boot flows
  • Experience with firmware, Linux drivers, or bare-metal development
  • Ability to diagnose complex problems at the hardware-software boundary

How we work

We value first-principles reasoning, direct communication, measurable engineering evidence, and collaboration across silicon, systems, software, and customer workloads.

11

Software Engineer, Acceleration Kernel Development

Shanghai, China

Apply now →

About the role

Build high-performance AI systems software across kernels, runtime, distributed execution, and device abstractions so models scale efficiently and operate reliably.

What you will do

  • Develop performance-critical software components and APIs in C++
  • Optimize kernel scheduling, memory movement, parallel execution, or device communication
  • Build benchmarks, profilers, tests, and continuous integration
  • Co-optimize with compiler, architecture, hardware, and model teams

What we look for

  • Strong C++, data structures, and systems programming
  • Understanding of concurrency, memory hierarchy, profiling, and Linux
  • Experience in runtime, kernels, distributed systems, or HPC is valuable
  • Commitment to correctness, maintainability, and developer experience

How we work

We value first-principles reasoning, direct communication, measurable engineering evidence, and collaboration across silicon, systems, software, and customer workloads.

12

Software Engineer, AI Compiler

Shanghai, China

Apply now →

About the role

Build the compiler toolchain that connects mainstream models to HOLYCORES hardware, improving correctness, performance, and developer experience through graph optimization and code generation.

What you will do

  • Design compiler frontends, intermediate representations, optimizations, and code generation
  • Enable new operators, data types, dynamic shapes, and hardware capabilities
  • Analyze compilation quality and runtime performance across the stack
  • Build automated tests, regression infrastructure, debugging tools, and documentation

What we look for

  • Background in computer science, compilers, or a related discipline
  • Strong C/C++ and knowledge of compiler IR or code generation
  • Experience with GCC, LLVM, MLIR, or an AI compiler framework
  • Commitment to software quality, interface design, and reproducible performance

How we work

We value first-principles reasoning, direct communication, measurable engineering evidence, and collaboration across silicon, systems, software, and customer workloads.

13

Software Engineer-AI Model Bring Up

Shanghai, China

Apply now →

About the role

Bring real AI models onto HOLYCORES platforms with correct and efficient execution across research, operators, compilers, kernels, and system performance.

What you will do

  • Port and validate language, vision, or multimodal models
  • Analyze operator coverage, numerical accuracy, memory, and performance
  • Optimize critical paths with compiler and kernel engineers
  • Create model baselines, automated regression, and reproducible benchmarks

What we look for

  • Experience with PyTorch and modern AI model architectures
  • Strong Python with C++ capability for performance-critical work
  • Understanding of numerical accuracy and training or inference tradeoffs
  • Data-driven cross-layer performance engineering

How we work

We value first-principles reasoning, direct communication, measurable engineering evidence, and collaboration across silicon, systems, software, and customer workloads.

14

Software Engineer, Metal Runtime (Core Systems)

Shanghai, China

Apply now →

About the role

Build high-performance AI systems software across kernels, runtime, distributed execution, and device abstractions so models scale efficiently and operate reliably.

What you will do

  • Develop performance-critical software components and APIs in C++
  • Optimize kernel scheduling, memory movement, parallel execution, or device communication
  • Build benchmarks, profilers, tests, and continuous integration
  • Co-optimize with compiler, architecture, hardware, and model teams

What we look for

  • Strong C++, data structures, and systems programming
  • Understanding of concurrency, memory hierarchy, profiling, and Linux
  • Experience in runtime, kernels, distributed systems, or HPC is valuable
  • Commitment to correctness, maintainability, and developer experience

How we work

We value first-principles reasoning, direct communication, measurable engineering evidence, and collaboration across silicon, systems, software, and customer workloads.

15

Software Engineer, Scale Out

Shanghai, China

Apply now →

About the role

Build high-performance AI systems software across kernels, runtime, distributed execution, and device abstractions so models scale efficiently and operate reliably.

What you will do

  • Develop performance-critical software components and APIs in C++
  • Optimize kernel scheduling, memory movement, parallel execution, or device communication
  • Build benchmarks, profilers, tests, and continuous integration
  • Co-optimize with compiler, architecture, hardware, and model teams

What we look for

  • Strong C++, data structures, and systems programming
  • Understanding of concurrency, memory hierarchy, profiling, and Linux
  • Experience in runtime, kernels, distributed systems, or HPC is valuable
  • Commitment to correctness, maintainability, and developer experience

How we work

We value first-principles reasoning, direct communication, measurable engineering evidence, and collaboration across silicon, systems, software, and customer workloads.

16

Sr Engineer, AI Kernel

Shanghai, China

Apply now →

About the role

Build high-performance AI systems software across kernels, runtime, distributed execution, and device abstractions so models scale efficiently and operate reliably.

What you will do

  • Develop performance-critical software components and APIs in C++
  • Optimize kernel scheduling, memory movement, parallel execution, or device communication
  • Build benchmarks, profilers, tests, and continuous integration
  • Co-optimize with compiler, architecture, hardware, and model teams

What we look for

  • Strong C++, data structures, and systems programming
  • Understanding of concurrency, memory hierarchy, profiling, and Linux
  • Experience in runtime, kernels, distributed systems, or HPC is valuable
  • Commitment to correctness, maintainability, and developer experience

How we work

We value first-principles reasoning, direct communication, measurable engineering evidence, and collaboration across silicon, systems, software, and customer workloads.

17

Technical Program Manager, Product Software

Shanghai, China

Apply now →

About the role

Connect customer workloads, product direction, and engineering execution by turning complex technology into clear requirements, milestones, decisions, and deliverables.

What you will do

  • Synthesize customer, developer, and internal requirements
  • Define product boundaries, priorities, roadmaps, and success metrics
  • Drive milestone-based collaboration across hardware, software, systems, and business teams
  • Surface risks, dependencies, and decisions through clear communication

What we look for

  • Experience in semiconductors, AI infrastructure, or systems software
  • Ability to understand complex technology and form product judgment
  • Strong program execution, cross-functional coordination, and writing
  • Focus on customer outcomes and reusable platform capabilities

How we work

We value first-principles reasoning, direct communication, measurable engineering evidence, and collaboration across silicon, systems, software, and customer workloads.