Production-Ready LLM Fine-Tuner & RL Researcher

Baseten; United States; Remote; USD 140,000 - 190,000; Full time

Job summary

Baseten is seeking an applied post-training research engineer to work with the world’s fastest-growing AI companies, posting-train open-source models that outperform frontier closed models on domain-specific tasks. You’ll design reward functions, environments, eval harnesses, and training pipelines that translate signal into production-ready models shipped to millions of users.

You will collaborate with customers to translate domain requirements into effective training curricula, with hands-on

Qualifications

• Hands-on experience training LLMs with reinforcement learning — demonstrated understanding of GRPO or PPO beyond recipe-level reproduction.

Responsibilities

• Design and run post-training pipelines: SFT, GRPO, DPO, RLVR, reward function engineering, and synthetic data generation.
• Build task-specific training environments and evals tailored to customer domains like healthcare, code generation, and legal, spanning multi-turn tool use, sandboxed execution, and agentic workflows.
• Work directly with customers to translate production data into training signal, designing reward loops from real usage patterns and handling distribution shift.
• Run and analyze training experiments end-to-end: diagnose reward hacking, importance sampling drift, and advantage estimation instabilities.
• Publish findings at top venues and contribute to Baseten's open-source training libraries.

Skills

LLM Fine-tuning

Reinforcement Learning

PPO/GRPO

Reward Engineering

Multi-turn Environments

Production ML Systems

Tools

Open-source training libraries

Job description

Baseten is seeking an applied post-training research engineer to work with the world’s fastest-growing AI companies, posting-train open-source models that outperform frontier closed models on domain-specific tasks. You’ll design reward functions, environments, eval harnesses, and training pipelines that translate signal into production-ready models shipped to millions of users.

You will collaborate with customers to translate domain requirements into effective training curricula, with hands-on