Frontend AI Compiler Engineer - Ingestion & IR

Lemurian Labs Inc.; Santa Clara (CA); On-site; USD 140,000 - 190,000; Full time

Benefits offered by this job

Equity

Medical/Dental/Vision

Retirement savings plan

Wellness benefits

Job summary

Lemurian Labs Inc. seeks a Front End Compiler Engineer to own the ingestion layer of a high-performance, portable AI compiler. You will parse, validate, and lower representations from PyTorch, StableHLO, ONNX, and MLIR dialects into our internal IR, enabling next‑gen AI models to run anywhere.

You will design the frontend, extend ingestion pipelines, ensure operator coverage, and collaborate with optimization teams to produce robust, verifiable IR and tooling for ML engineers.

Qualifications

• BS degree or equivalent practical experience in CS or related field.
• 2+ years working with ML optimization tools and libraries.
• Experience ingesting from ML frameworks such as PyTorch, TensorFlow/JAX, or ONNX.
• 2+ years in C/C++ and 2+ years in Python.
• Strong documentation and communication skills.
• Knowledge of quantization, sparsity, or model-level optimization.

Responsibilities

• Design, develop, and maintain the frontend of our heterogeneous AI compiler, including parsing, validation, and IR lowering stages.
• Build and extend ingestion pipelines for ML frameworks and representations including PyTorch, StableHLO, ONNX, and MLIR-based dialects.
• Define and evolve the interface between external model representations and our internal compiler IR.
• Ensure correctness and completeness of operator coverage across supported frameworks and hardware targets.
• Collaborate with graph optimization and code generation teams to ensure clean, well-structured IR that enables downstream transformations.
• Use performance and correctness data to identify gaps in coverage and drive improvements.
• Contribute to documentation and tooling that helps ML engineers understand and debug the ingestion process.

Skills

ML optimization tools

ML framework ingestion

C/C++

Python

Documentation

Model optimization techniques

Education

BS in Computer Science or equivalent

MS/PhD preferred

Tools

MLIR

StableHLO

XLA

ONNX dialects

Job description

Lemurian Labs Inc. seeks a Front End Compiler Engineer to own the ingestion layer of a high-performance, portable AI compiler. You will parse, validate, and lower representations from PyTorch, StableHLO, ONNX, and MLIR dialects into our internal IR, enabling next‑gen AI models to run anywhere.

You will design the frontend, extend ingestion pipelines, ensure operator coverage, and collaborate with optimization teams to produce robust, verifiable IR and tooling for ML engineers.