Senior ML Infrastructure Engineer (Post-Training & RL Environments)

preference model • United States

Visa Sponsorship Relocation

This Job is No Longer Active This position is no longer accepting applications

AI Summary

Build and scale production-grade ML infrastructure for post-training research on large language models and reinforcement learning environments. Design scalable compute, scheduling, and data systems while collaborating with research teams to accelerate self-directed learning. Requires expertise in distributed systems, cloud platforms, and ML frameworks like PyTorch/JAX.

Key Highlights

Build scalable infrastructure for high-throughput LLM post-training and RL environments

Collaborate directly with research engineers to translate needs into infrastructure solutions

Focus on reliability, benchmarking, and tooling for reproducible experimentation

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.

Key Responsibilities

Design, build, and scale compute, scheduling, and data infrastructure for post-training research on RL environments

Develop and maintain core ML framework primitives and internal tooling for researchers

Build evaluation, benchmarking, monitoring, logging, and debugging systems for reliability at scale

Partner with Research Engineers to translate research needs into infrastructure requirements

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

Technical Skills Required

Distributed Systems Cloud Platforms (AWS/GCP) PyTorch or JAX

Interested in relocating to United State? Check out our comprehensive Relocation Jobs in United State page with detailed relocation packages and benefits.

Benefits & Perks

Competitive cash and equity compensation (>90th percentile)

Health, vision, dental, and 401K benefits

Visa sponsorship and relocation support available

Job Description

Preference Model is building automated ML research engineering.Existing frontier models are brittle when applied to real-world ML tasks. The present bottleneck is the lack of high-quality RL training environments. Our first step is to build RL environments that reflect real-world complexity, with diverse tasks and robust reward functions.Our founding team has previous experience on Anthropic’s data team building data infrastructure, and datasets behind Claude. We are partnering with leading AI labs to push AI closer to achieving its transformative potential.

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.