Staff ML Engineer — Ultra-Low-Latency Inference

Inworld; Mountain View (CA); Hybrid; USD 270,000 - 500,000; Full time

Benefits offered by this job

Relocation assistance

Equity options

Comprehensive benefits

Job summary

A tech company in Mountain View seeks talented engineers for a role emphasizing high-performance systems, inference optimization, and model acceleration. You will thrive in ambiguity, tackle unclear problems, and design impactful solutions. The position offers a competitive base salary between $270,000 and $500,000, along with bonuses, equity, and benefits. Ideal candidates hold a relevant PhD or equivalent experience and have a knack for full-cycle ownership in engineering projects. Join a dynamic team prioritizing performance and collaboration.

Qualifications

• Deep understanding of inference optimization frameworks.
• Hands-on experience with model acceleration techniques.
• Proficiency in C++, CUDA, Rust, or optimized Python.
• Experience with Kubernetes and multi-GPU inference.
• Track record of impactful public work in systems programming.
• Ability to own models from research to production.

Responsibilities

• Transform unclear problems into clear solutions.
• Prioritize impact over theoretical optimizations.
• Ensure stability and performance before launch.
• Foster collaboration and strong team culture.

Skills

Inference Optimization

Model Acceleration

High-Performance Systems

Distributed Systems & Scaling

Public work

Full-cycle ownership

PhD in CS/Physics/Math

Education

PhD in CS, Physics, Math, or equivalent experience

Job description

A tech company in Mountain View seeks talented engineers for a role emphasizing high-performance systems, inference optimization, and model acceleration. You will thrive in ambiguity, tackle unclear problems, and design impactful solutions. The position offers a competitive base salary between $270,000 and $500,000, along with bonuses, equity, and benefits. Ideal candidates hold a relevant PhD or equivalent experience and have a knack for full-cycle ownership in engineering projects. Join a dynamic team prioritizing performance and collaboration.