← All roles

Full-Time Engineer: AI Software Engineer

OpenInfer
Apply on company site
Hybrid (Bay Area, CA)Full-timePosted 3mo ago

About the role

Rust Software Developer needed to work on local AI inference, contribute to API front-end and core systems, and help deliver improvements to LLM inference across client platforms.

Responsibilities

  • Develop and maintain LLM inference engine written in Rust
  • Deploy Rust to all major client platforms (Windows, Linux, MacOS, Android, iOS)
  • Maintain GitHub actions to build & release software
  • Maintain end-to-end integrations with Rust across major customer development platforms (React.Native, Java/Kotlin, Swift, C/C++, Python)
  • Debug and troubleshoot issues in our API and related infrastructure
  • Collaborate with product and AI teams to integrate new features

Qualifications

  • Ideally at least 1-3 years of experience with Rust (personal projects, coursework, or previous work)
  • Proficiency in async Rust and concurrent programming
  • Strong generalist comfortable with learning and growth attained by tackling out-of-expertise problems
  • Strong problem-solving skills and attention to detail
  • Familiarity with Axum, Actix, or other Rust web frameworks
  • Understanding of containerization (Docker) and cloud services
  • Familiarity with GitHub Actions and CI/CD
  • 3 years experience in C++
  • Experience with Android NDK and integrating Rust into mobile applications
  • Working with LLMs and local inference engines like llama.cpp or Ollama
  • Familiarity with REST design and FFI integration into C, Python, etc

Skills

Required:RustAPI development and integrationCross-platform deployment

Benefits

  • Medical, Dental, and Vision benefits
  • Flexible Paid Time Off, 10 days
  • Parental Leave
  • 401(k) Plan with company matching
  • Snacks and coffee to keep you energized
Last updated Oct 25, 2026. Interested? Apply on the company site.
OpenInfer logo

About OpenInfer

OpenInfer — Inference OS for the Agentic Era

OpenInfer is the Inference OS for the agentic era — run AI agents on the CPUs, GPUs, and NPUs you already own, at the best cost and speed, with no cloud lock-in.

AI infrastructureCPUsGPUsInference OSNPUsbessemer-ai-infrastructure-2026distributed inferenceedge computing
Company profileWebsite

More open roles at OpenInfer