Senior Machine Learning Platform Engineer (RL Environment Infrastructure)

preference model • United State

Remote Visa Sponsorship Relocation

Apply Now

AI Summary

Own the end-to-end infrastructure and automation pipeline for RL environments, ensuring seamless delivery to partner labs. Build and maintain Karotte, a developer framework, while scaling containerized execution across CPU/GPU/TPU with strict sandboxing. Collaborate with researchers to automate tedious tasks and improve platform reliability.

Key Highlights

Build and automate delivery pipelines for RL environments to partner labs (containerization, validation, and submission automation)

Develop and maintain Karotte, an open-source RL environment framework, with API design and migration support

Scale and secure infrastructure for environment execution (CPU/GPU/TPU, sandboxing, resource limits, and untrusted code isolation)

Key Responsibilities

Design and automate integrations to deliver RL environments to partner labs (container images, submission formats, and validation checks)

Build and maintain Karotte, an open-source framework for defining RL environments, including API design, releases, and migrations

Scale and secure infrastructure for building, running, and grading environments across CPU/GPU/TPU with sandboxing and resource limits

Develop internal tools (CLI, documentation, data catalog, access controls, and monitoring) for environment builders

Collaborate with environment builders and post-training researchers to address pain points and automate recurring tasks

Ensure end-to-end automation of environment delivery pipelines within six months, reducing manual intervention

Looking to advance your Devops career with relocation support? Explore Devops Jobs with Relocation Packages that include comprehensive packages to help you move and settle in your new role.

Technical Skills Required

Python Containers and Orchestration (Docker, Kubernetes) Cloud Platforms (GCP, AWS)

Benefits & Perks

Competitive cash and equity compensation (>90th percentile)

Visa sponsorship available

Relocation support available

Health, vision, dental, and 401K benefits

Onsite lunch and weekly snack orders

Discover our full range of relocation jobs with comprehensive support packages to help you relocate and settle in your new location.

Nice to Have

Experience building RL environments or eval harnesses (e.g., Terminal-Bench, SWE-bench)

Familiarity with RL post-training/inference stacks (e.g., Ray, SkyPilot, vLLM)

Experience with sandboxing technologies (e.g., Firecracker, gVisor)

Background in maintaining open-source developer frameworks with external users

Job Description

Preference Model is a superintelligence data research company. We build RL environments for training capable, better-aligned superintelligences.Almost every aspect of how a model behaves is shaped by the reward signals it's trained on. The biggest problem with AIs today is that they don't always do what we intend. Sometimes that's because they aren't capable enough, and sometimes it's because they aren't aligned. Both problems come down to the training objectives.

Want the full job description? Read the complete details on LinkedIn, the original posting.

Continue on LinkedIn

This is a short excerpt. All rights to the full description belong to its original publisher.