ML Compiler Engineer, Edge-AI & Low-Latency

Femtosense; San Bruno (CA); On-site; USD 100,000 - 140,000; Full time

Benefits offered by this job

401(k)

Medical insurance

Vision insurance

Disability insurance

Paid maternity leave

Paid paternity leave

Child care support

Job summary

A tech company specializing in AI solutions, based in San Bruno, is looking for a Compiler Developer. The role involves building and maintaining model ingestion pipelines, implementing graph transformations, and optimizing execution for a custom ML compiler. Candidates should have over 2 years of experience in compilers or edge AI, with proficiency in Python and/or C++, and familiarity with tools like MLIR or LLVM. The position offers benefits including 401(k) and medical insurance.

Qualifications

• 2+ years of experience in compilers and/or edge-AI.
• Experience with graph-level transformations or ML model internals.
• Familiarity with optimization techniques.

Responsibilities

• Build and maintain model ingestion pipelines (e.g., PyTorch / ONNX → internal IR).
• Implement graph transformations such as operator decomposition and canonicalization.
• Debug correctness and numerical issues across transformations.

Skills

Proficiency in Python

Proficiency in C++

Experience with MLIR

Experience with LLVM

Experience with TVM

Experience with XLA

Understanding of deep learning models

Ability to reason about correctness and performance tradeoffs

Job description

A tech company specializing in AI solutions, based in San Bruno, is looking for a Compiler Developer. The role involves building and maintaining model ingestion pipelines, implementing graph transformations, and optimizing execution for a custom ML compiler. Candidates should have over 2 years of experience in compilers or edge AI, with proficiency in Python and/or C++, and familiarity with tools like MLIR or LLVM. The position offers benefits including 401(k) and medical insurance.