Our client is a pre-seed startup working in the AI model-evaluation space, building the infrastructure that measures how the leading AI models perform on rigorous, domain-specific tasks. They are backed by a top Silicon Valley seed fund and partner with major players across the AI ecosystem. This is an early, high-autonomy environment where you would help shape the engineering culture and own significant parts of the platform from day one.

Founded 2024, about 25 people, Industry: AI and Software Development.

We are hiring a generalist software engineer to join the platform team and build the systems that run large-scale model evaluations end to end. You will work across the stack in a fast-moving environment, taking open-ended problems and shipping solutions independently. This is a pure individual-contributor role where you stay hands-on every day.

What you will be doing

• Building and maintaining the platform that runs model benchmarks end to end: backend libraries, web platform, cloud infrastructure, and tooling
• Working across the full stack as a generalist, spanning backend services and frontend features as the team needs
• Taking fuzzy, open-ended problems and independently designing, building, and shipping solutions
• Running code and architecture reviews for other engineers
• Partnering closely with the research team so the infrastructure meets their evaluation needs

Tech stack: Python, Django, React, TypeScript, AWS

• 2 to 6 years of professional experience in full-stack or platform engineering
• A track record of building products from the ground up (0-to-1), whether at a major tech company, a venture-backed startup, or as a founder

• Experience founding a company or working at an early-stage startup
• A history of building production systems of meaningful scale and scope
• Strong, hands-on production Python in a professional setting
• Frontend experience with React and TypeScript
• An undergraduate CS degree from a top-25 program (a top-5 program stands out if your experience is lighter)

• Get in at the pre-seed stage and own large parts of the platform from day one
• Real autonomy over architecture and technical decisions
• Build the infrastructure that runs AI evaluations at scale, alongside a strong, research-driven team

• Location: San Francisco, CA
• Work policy: On-site, 5 days per week
• Compensation: $150K to $210K plus equity
• Visa sponsorship: Open to visa transfers (for example OPT, H-1B transfers); sponsorship available for exceptional candidates
• Employment type: Full-time