Skip to main content

Build AI

ML Engineer, Inference Optimization

  • Confirmed live in the last 24 hours
  • $200k–$320k
  • Mid level
  • Full-time
  • On-site · San Francisco
  • Added 2 months ago

About this role

Build AI is seeking an ML Engineer to optimize inference performance and dramatically reduce compute costs. This role focuses on improving latency, throughput, and cost-effectiveness of models, working closely with research and product teams. The ideal candidate will be passionate about cost-driven optimization and scaling AI models efficiently.

What you'll do

  • Optimize inference performance (latency, throughput, cost)
  • Implement techniques like kernel optimization, batching, and quantization
  • Profile and identify bottlenecks in inference pipelines
  • Collaborate with research and product on cost-effective models
  • Build and maintain serving and evaluation paths
  • Establish cost as a primary metric

What they're looking for

  • ML/Systems Engineering
  • Inference Optimization
  • Python
  • Rust
  • PyTorch
  • Profiling Tools (e.g., Nsight, PyTorch Profiler)
  • CUDA

Benefits

  • Competitive pay
  • Medical, dental, and vision
  • Housing subsidy ($2k/month)
  • Relocation support
  • Wellness benefits
  • Daily lunch and dinner
Apply with Autofill

Opens the application — the Jobs AI extension fills it for you. Set up autofill

Opens the official application on the employer’s site. No login required.

Build AI

Industry
Technology & Software
View all jobs at Build AI

Likely interview questions

  • Describe a time you significantly improved inference performance. What techniques did you use and what were the results?
  • How do you approach profiling a complex ML pipeline to identify bottlenecks?