Member of Technical Staff - ML Platform Engineer

The role

You will own the systems that take RL environments from a builder's repo to a lab's training run. This includes managing the Karotte framework, internal platform infrastructure, and integrations for partner labs.

What you will do

• Own integrations that deliver environments to partner labs by building container images and automating checks.
• Build and maintain the Karotte open-source environment framework.
• Run and scale infrastructure that builds, runs, and grades environments across CPU, GPU, and TPU.
• Build internal tools including CLI, docs, data catalog, access controls, and run monitoring.
• Partner with environment builders and post-training researchers to turn pain points into platform features.

Required qualifications

• 5+ years of experience building and owning ML Platform Engineering
• Strong software engineering fundamentals
• Track record of building and operating production infrastructure or developer platforms
• Hands-on experience with containers and orchestration (Docker, Kubernetes, or similar)
• Experience with at least one major cloud platform (GCP, AWS, or similar)
• Working understanding of how to run untrusted code safely
• Experience owning migrations, release processes, or delivery pipelines and automating them
• Extensive hands-on use of coding agents (Claude Code, Cursor, Codex, or similar)
• Proficiency in Python, including writing libraries and APIs

Nice to have

• Experience building RL environments, eval harnesses, or agent benchmarks (Terminal-Bench, SWE-bench, or similar)
• Familiarity with RL post-training and inference stacks (verl, Ray, SkyPilot, vLLM, SGLang, or similar)
• Built sandbox or code-execution infrastructure (microVMs such as Firecracker, gVisor, or similar)
• Early platform or infrastructure engineer at a startup
• Worked as a forward deployed or integrations engineer
• Built developer tooling or internal platforms used by ML researchers
• Maintained an open-source developer framework with real external users

Benefits

• Competitive cash and equity compensation (>90th percentile)
• Ownership and autonomy in a fast moving startup environment
• Opportunity to work alongside senior and staff engineers from frontier labs and infrastructure companies, plus top ML engineers
• Health, vision, dental, benefits
• 401K match
• Lunch provided everyday onsite
• Weekly snack orders
• Visa sponsorship & relocation support available

Before you apply

• Visa sponsorship & relocation support available

About the company

Preference Model is a superintelligence data research company that builds RL environments for training capable, better-aligned superintelligences. The founding team has previous experience on Anthropic’s data team.