Member of Technical Staff - ML Infrastructure Engineer, RL Post-training

The role

This role involves building scalable infrastructure to power post-training on large language models. You will design compute, scheduling, and data infrastructure for in-house RL environments.

What you will do

• Design, build, and scale compute, scheduling, and data infrastructure for post-training research
• Develop and maintain core ML framework primitives and internal tooling
• Build evaluation and benchmarking infrastructure
• Build monitoring, logging, debugging tooling, and automated testing and deployment systems
• Partner with Research Engineers to translate research needs into infrastructure requirements

Required qualifications

• Strong software engineering fundamentals
• Hands-on experience building production-grade LLM inference and training infrastructure
• Experience building LLM training/inference internals such as transformers, distributed training, and working on inference libraries like vLLM, SGLang, Megatron
• Experience working on RL training frameworks like Slime, veRL, Ray Train, SkyRL, Miles
• Significant experience and understanding of distributed systems principles
• Hands-on experience with cloud platforms (AWS, GCP) and container orchestration (Kubernetes)
• Experience building systems for high-throughput, low-latency workloads
• Experience with data engineering tools and building robust, scalable data pipelines
• Proficiency in core ML frameworks such as PyTorch or JAX
• Ability to balance production rigor with the pace of fast-moving research

Nice to have

• experience building production-grade LLM inference and training infrastructure (ideally from the ground up)

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

Before you apply

• Visa sponsorship & relocation support available

About the company

Preference Model is a superintelligence data research company. They build RL environments for training capable, better-aligned superintelligences.