Lead AI Compiler & Runtime Architect (Hybrid US)

Coley S Home Remodeling; Palo Alto (CA); Hybrid; USD 200,000 - 350,000; Full time

Benefits offered by this job

Medical, dental, vision

401(k) with company match

Unlimited vacation

Parental benefits

Employee assistance program

Job summary

HTEC Group, Inc. in Palo Alto, CA is hiring for a role shaping the software foundation for next-generation AI compute platforms.

You will work on compilers, AI runtimes, graph optimization, and hardware-aware execution in close collaboration with inference engineers, ML scientists, and hardware specialists. This position offers opportunities to optimize AI workloads at scale and contribute to state-of-the-art AI infrastructure, partnering with global teams on software-hardware co-design.

Qualifications

• Degree in CS, Engineering or related field.
• Strong programming in C/C++ and Python on Linux.
• Experience applying AI to software optimization.
• Familiarity with AI runtimes, compilers, and hardware-aware design.

Responsibilities

• Build and optimize compiler and runtime infrastructure for AI workloads.
• Enable efficient ML model execution across GPUs and accelerators.
• Profile, benchmark, and fix performance bottlenecks.
• Collaborate with hardware and software teams for co-design.

Skills

C/C++

Python

Linux

ML fundamentals

Education

BSc/MSc/PhD in CS/Engineering

Tools

LLVM

MLIR

ONNX Runtime

Triton

Job description

HTEC Group, Inc. in Palo Alto, CA is hiring for a role shaping the software foundation for next-generation AI compute platforms.

You will work on compilers, AI runtimes, graph optimization, and hardware-aware execution in close collaboration with inference engineers, ML scientists, and hardware specialists. This position offers opportunities to optimize AI workloads at scale and contribute to state-of-the-art AI infrastructure, partnering with global teams on software-hardware co-design.