Research Scientist, AI

Pramaana Labs • Palo Alto, CA

5d

About The Position

Pramaana Labs is a frontier AI lab building a verification layer for AI. It transforms complex human knowledge—such as tax codes, legal rules, clinical guidelines, and security protocols—into formal representations that support inspectable and verifiable reasoning. Its architecture pairs models trained to formalize and reason with a symbolic world model encoded in Lean 4.

The Research Scientist, AI will develop approaches to improve the accuracy, coverage, efficiency, and generalization of Pramaana’s domain formalizer, autoformalizer, and prover. The role spans model training, data quality, representations, and evaluation, and involves collaboration with an RL Scientist, Research Engineers, and Formal Methods experts.

The successful candidate will lead research at the intersection of foundation models, formal reasoning, and verification; develop model training and post-training methods; and conduct hands-on research in reinforcement learning, synthetic data generation, reasoning, and agentic AI. They will own end-to-end research initiatives, establish technical direction, guide researchers and engineers while staying technically engaged, develop rigorous benchmarks and evaluation methods, and work with engineering to bring research advances into production.

Requirements

• Demonstrated track record of high-impact research, including projects successfully deployed and materially advancing a product, core technology, or organizational capabilities and direction.
• Deep hands-on experience in foundation model training and post-training, including one or more of large-scale pretraining, reinforcement learning, reasoning-focused training, or synthetic data generation.
• Strong technical depth in modern AI research, including frontier language models, agentic systems, multi-step reasoning, or structured prediction.
• Proficiency in Python and modern machine-learning frameworks such as PyTorch or JAX, with experience implementing and scaling training experiments.
• Exceptional research judgment and experimental rigor, including identifying promising directions, formulating hypotheses, designing meaningful evaluations, and distinguishing genuine advances from incremental gains.
• Demonstrated technical leadership and independence, including driving ambitious research initiatives, mentoring scientists, and collaborating across research and engineering while remaining a strong individual contributor.

Nice To Haves

• Direct experience training or post-training frontier-scale models, including distributed training, large-scale reinforcement learning, or inference-time scaling.
• Research experience in neuro-symbolic AI, autoformalization, automated theorem proving, program synthesis, or formal verification.
• Strong research record demonstrated through influential publications, deployed research breakthroughs, or substantial improvements to state-of-the-art model capabilities.

Responsibilities

• Lead research at the intersection of foundation models, formal reasoning, and verification.
• Develop novel model training and post-training approaches for translating complex domain knowledge into structured representations and enabling precise, verifiable reasoning.
• Conduct hands-on research in reinforcement learning, synthetic data generation, reasoning, and agentic AI to advance model capabilities, generalization, and efficiency.
• Own end-to-end research initiatives, identify high-impact directions, set technical strategy, and guide teams of researchers and engineers while remaining involved in technical work.
• Develop benchmarks and evaluation methodologies to measure reasoning capabilities, robustness, and generalization, and use experimental insights to improve models.
• Partner with engineering to translate research breakthroughs into production capabilities and improve technology performance and reliability.
• Collaborate with an RL Scientist, Research Engineers, and Formal Methods experts on research, experimentation, and the faithful representation of source knowledge.

What This Job Offers

• Job Type: Full-time
• Career Level: Senior
• Education Level: No Education Listed