Compiler Engineer

TetraMem - Accelerate The World; San Jose (CA); On-site; USD 160,000 - 300,000; Full time

Job summary

TetraMem — Accelerate The World is seeking engineers to design and maintain compiler toolchains that translate ML models into optimized workloads for our analog in-memory computing hardware. You will develop runtimes, libraries, and SDKs to deploy AI across our accelerators and implement advanced compiler optimizations to maximize performance and energy efficiency.

Collaborate with ML engineers on model conversion, validation, benchmarking, and deployment, and work with hardware teams to

Responsibilities

• Design, develop, and maintain compiler toolchains for translating ML models to optimized workloads on TetraMem hardware.
• Develop runtime systems, libraries, and SDK components for AI deployment on accelerators.
• Implement compiler optimizations: graph transformations, fusion, memory optimization, scheduling, code generation.
• Research techniques to improve inference speed, latency, throughput, and power across AI workloads.
• Collaborate with ML engineers for model conversion, validation, benchmarking, and deployment.
• Co-design software and hardware features with architects to improve performance and usability.

Job description

Responsibilities

• Design, develop, and maintain compiler toolchains that translate machine learning models from industry-standard frameworks into optimized workloads for TetraMem’s analog in‑memory computing hardware.
• Develop runtime systems, software libraries, and SDK components that enable efficient deployment, execution, and management of AI applications on TetraMem accelerators.
• Implement compiler optimizations, including graph transformations, operator fusion, memory optimization, scheduling, and code generation to maximize performance and energy efficiency.
• Research and develop innovative techniques to improve machine learning inference speed, latency, throughput, and power consumption across a wide range of AI workloads.
• Collaborate closely with machine learning engineers to support model conversion, validation, optimization, benchmarking, and deployment.
• Partner with hardware architects and silicon engineering teams to co‑design software and hardware features that improve system performance, programmability, and usability.
• Develop performance analysis, profiling, debugging, and benchmarking tools to evaluate and optimize AI workloads on current and future TetraMem platforms.
• Integrate and support industry‑standard machine learning frameworks and model formats, including PyTorch, TensorFlow, ONNX, and other emerging AI ecosystems.
• Lead technical design reviews, contribute to software architecture decisions, and establish best practices for scalable, maintainable, and high‑quality software development.
• Mentor junior engineers, contribute to technical documentation, and help define the long‑term roadmap for TetraMem’s compiler, runtime, and SDK technologies.

Requirements

• MS or PhD in Computer Engineering/CS/EE
• 5+ years industry experience as a compiler engineer or developer
• Experience developing compilers for GPU, dataflow compilers, or ML compilers
• Startup mindset/experience

Experience in one or more of the following areas considered a strong plus:

• Experience in RISC‑V CPU/VPU kernel development and optimization
• Experience providing technical leadership and/or guidance to other engineers
• Knowledge of popular CPU/GPU compilers such as GCC, Clang
• Knowledge of ML compilers such as MLIR
• Experience with LLVM and other open‑source compiler libraries and tools
• Publications on compilation of ML or dataflow programs for HW acceleration

Salary Range: $160,000 - $300,000 / year

TetraMem celebrates diversity and is committed to creating an inclusive environment for all employees. We are proud to be an Equal Opportunity Employer and welcome applicants from all backgrounds. Qualified candidates will receive consideration for employment without regard to race, color, religion, creed, sex, gender identity or expression, sexual orientation, national origin, ancestry, age, marital status, medical condition, disability, genetic information, military or veteran status, or any other characteristic protected by applicable federal, state, or local law.

TetraMem is committed to providing reasonable accommodations to qualified applicants with disabilities throughout the recruitment process. Applicants requiring accommodation may contact Human Resources for assistance.