Summary
What you’ll impact
The Senior Machine Learning Research Scientist defines and drives the post‑training roadmap for large language models, including fine‑tuning, preference optimization, reward modeling, and reinforcement learning. Using Python‑based ML frameworks and cloud compute, the scientist implements supervised fine‑tuning, RLHF/RLAIF, DPO, and large‑scale evaluation to build reliable, efficient models and develop quality benchmarks. The role collaborates with security researchers and engineering teams, translating research insights into production‑ready capabilities while mentoring peers on alignment and robustness practices.
Responsibilities
What you'll do
- Own Post-Training Strategy: Drive the post-training roadmap (fine-tuning, preference optimization, reward modeling, RL, distillation) to make models more capable, reliable, and aligned.
- Push Efficiency & Evals: Make models serve reliably at scale, and build the benchmarks that measure quality and catch regressions.
- Ground Research in Reality: Turn our security experts' tradecraft into model capabilities and ship your techniques into production.
- Stay at the Frontier: Track post-training and efficiency research and bring the best ideas in.
Requirements
What you’ll bring
- Research Pedigree: PhD in CS, ML, or related field, or equivalent experience with a strong track record.
- Post-Training Depth: Hands-on experience with SFT, RLHF/RLAIF, DPO, and reward modeling.
- Practical Results: You train, fine-tune, and evaluate models, and make research work in practice.
- Engineering Strength: You implement your own ideas and run them at scale.
- Range & Judgment: You drive strategy broadly or go deep on one hard problem as needed.
- Collaboration: You work well across teams and care about the outcome, not just your slice.