Artificial Intelligence, Machine Learning, Healthcare, Biotechnology, Software Development

Research Scientist, Reinforcement Learning

Palo Alto, CAOnsiteFull TimePosted 2 months ago

Is this role right for you?

Upload your resume and get a skill-by-skill breakdown — see exactly where you match, where you're close, and what to highlight. Not a mystery percentage.

Get a tailored resume highlighting what this role needs.

Required skills

Reinforcement Learning
RLVR
test-time RL
Lean kernel
autoformalization
proving
RL algorithms
data pipelines
evals
formal environments

Nice to have

formal verification
Lean
Coq
Isabelle
NeurIPS
ICML

Role summary

Pramaana Labs, a frontier AI lab, is seeking an RL Post-Training Researcher to advance their verification layer for AI. This role involves scaling Reinforcement Learning from Human Feedback (RLHF) to new domains using verified rewards from a Lean kernel, pushing autoformalization, and innovating on RL algorithms, data, and evaluations. The researcher will define how models leverage test-time compute for long-horizon logical tasks. The ideal candidate has deep research experience in RL applied to reasoning models, experience with RLVR or test-time RL, strong algorithmic and systems intuition, and high autonomy. A background in formal verification or a strong publication record is a plus.

Company

Pramaana Labs is a frontier AI lab building the verification layer for AI. Founded in 2025 and headquartered in Palo Alto, we turn complex human knowledge, including tax codes, legal rules, clinical guidelines and security protocols, into a formal representation, so every AI answer can be traced, challenged, and proved.

Pramaana's architecture pairs foundation models trained to formalize and reason with a symbolic world model encoded in Lean 4. Pramaana was founded by a team out of Google, DeepMind, and Glean, combining frontier AI researchers and formal methods experts.

The role

We're training foundation models to natively interact with symbolic world models. As an RL Post-Training Researcher, you'll take foundation models and scale their reasoning capabilities: applying RLVR to new domains using verified rewards from the Lean kernel, pushing the frontier of autoformalization and proving, and innovating on RL algorithms, data, and evals. Your work will also define how our models leverage test-time compute to solve long-horizon logical tasks.

What you'll actually work on

Scale RLVR to new, real-world domains using the Lean kernel as a deterministic reward signal.
Design and implement novel RL algorithms and test-time compute optimizations tailored for formal environments and proof search.
Push the frontier of autoformalization, training models to map highly technical natural language into strict formal specifications.
Curate data and build evals that tightly correlate with verifiable downstream reasoning capabilities.
Own the whole loop: rollout sampling, reward design, the update, the eval.

You Will Thrive in This Role If You Have

Deep, hands-on research experience in reinforcement learning applied to reasoning models at scale.
Experience working with RLVR, test-time RL, or exact deterministic reward signals.
Strong algorithmic and systems intuition — comfortable writing custom RL loops, managing data pipelines, and building robust evals from scratch.
High autonomy: the ability to take a fuzzy problem area and independently drive it to state-of-the-art results without day-to-day direction.

Especially Strong Candidates May Also Have

A background in formal verification (Lean, Coq, or Isabelle)
A strong publication record in top-tier venues (NeurIPS, ICML, ICLR).

Ready to apply?

You'll be redirected to Pramaana Labs's application page.