Member of Technical Staff, Post-Training

What you'll do

• Design post-training methods and systems, including fine-tuning, reinforcement learning, preference optimization, and reward modeling.
• Turn research and partner needs into experiments, evaluation frameworks, pipelines, and production-quality implementations.
• Identify repeatable solutions and productize them into reusable software and platforms.

What they ask for

• 3+ years of demonstrated strength in post-training, fine-tuning, or model-evaluation work.
• Strong Python skills and ability to write clean, efficient, scalable software.
• Hands-on experience with modern ML tooling, particularly PyTorch, and large-scale data, training, or evaluation workflows.
• Experimental judgment and experience designing systems, including tradeoffs among quality, scale, reliability, and reuse.

Nice to have

• Experience building large-scale ML systems, LLM/agent benchmarks, evaluation methodologies, annotation systems, or data-quality frameworks.
• Research, open-source contributions, technical leadership, or experience productizing research into reusable platforms.

Pay

$200K – $350K USD base salary

Tools

Python, PyTorch, RL, SFT, LoRA/PEFT, RLHF, DPO, PPO

AI focus

Develop and evaluate post-training methods and systems for frontier models, including supervised fine-tuning, reinforcement learning, preference optimization, reward modeling, and human-feedback and evaluation workflows.