Post-Training Research Scientist (LLMs) — Experimental Track

Key Responsibilities:

• Design and run post-training experiments on frontier and open-weight LLMs.
• Translate raw annotation artifacts into training-ready datasets.
• Prototype new reward signals beyond pairwise preferences.

About You:

• We’re looking for a researcher who thrives with autonomy and brings a strong execution mindset.
• You are opinionated about data quality, pragmatic about tradeoffs, and comfortable moving quickly with incomplete information.
• You have strong experimental instincts to design, run, and interpret messy experiments.

Minimum Qualification:

• PhD (or equivalent experience) in ML/AI, applied math, stats, or adjacent.
• Hands-on experience with LLM post-training (at least one of SFT/DPO/RLHF/RLVR).
• Solid Python + PyTorch/JAX; comfortable with training infra basics.