Staff ML Engineer: Build Ultra-Fast AI at Scale (Relocation)

Inworld AI; Mountain View (CA); On-site; USD 270,000 - 500,000; Full time

Benefits offered by this job

Relocation assistance

Equity options

Comprehensive benefits package

Job summary

A tech-driven AI firm in Mountain View is seeking a high-performance systems engineer. This role demands expertise in inference optimization, model acceleration, and a deep understanding of performance tuning in C++, CUDA, and more. Candidates should possess a PhD or equivalent experience. Compensation ranges from $270,000 to $500,000 plus bonuses and equity. Relocation assistance is provided for successful candidates looking to innovate in a collaborative atmosphere.

Qualifications

• Deep understanding of modern serving frameworks like vLLM or TRT-LLM.
• Hands-on experience with quantization and caching strategies.
• Proficiency in profiling code and optimizing performance for NVIDIA GPUs.

Responsibilities

• Take models from research, containerize and optimize for production.
• Communicate and collaborate closely with the team.
• Design prototypes to explore unclear problems.

Skills

Inference Optimization

Model Acceleration

High-Performance Systems

Distributed Systems & Scaling

Public work

Full-cycle ownership

PhD in CS, Physics, Math or equivalent

Education

PhD in Computer Science or equivalent

Tools

C++

CUDA

Rust

Python

Kubernetes

Job description

A tech-driven AI firm in Mountain View is seeking a high-performance systems engineer. This role demands expertise in inference optimization, model acceleration, and a deep understanding of performance tuning in C++, CUDA, and more. Candidates should possess a PhD or equivalent experience. Compensation ranges from $270,000 to $500,000 plus bonuses and equity. Relocation assistance is provided for successful candidates looking to innovate in a collaborative atmosphere.