Platform Engineer - LLM Benchmarking & Infra

davidjoseph-co; San Francisco (CA); On-site; USD 150,000 - 210,000; Full time

Job summary

Vals AI in San Francisco, CA, is seeking a generalist software engineer to join the platform team building infrastructure for LLM evaluations at scale. You will work across the stack from Python backend to React frontend, delivering production-grade solutions with high autonomy.

Ideal candidates have 2–6 years in full-stack or platform engineering, hands-on Python and React experience, and a track record of shipping meaningful systems.

Qualifications

• 2–6 years of experience in full-stack or platform engineering.
• 0-to-1 product-building experience in big tech or startups.
• Founding a company or working at an early-stage startup is strongly preferred.
• Experience building systems of meaningful scope in production.
• Production Python expertise; React/TypeScript frontend experience.

Responsibilities

• Builds and maintains the platform that runs LLM benchmarks end to end.
• Works across the full stack: backend Python/Django and frontend React/TypeScript.
• Designs, builds, and ships solutions for fuzzy, open-ended problems.
• Performs code reviews and architecture reviews for teammates.
• Collaborates with research to ensure infrastructure meets evaluation needs.

Skills

Full-stack development

Independent problem solving

Code reviews

Education

Undergraduate CS degree

Tools

Python

Django

React

TypeScript

AWS

Job description

Vals AI in San Francisco, CA, is seeking a generalist software engineer to join the platform team building infrastructure for LLM evaluations at scale. You will work across the stack from Python backend to React frontend, delivering production-grade solutions with high autonomy.

Ideal candidates have 2–6 years in full-stack or platform engineering, hands-on Python and React experience, and a track record of shipping meaningful systems.