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 RoleAs a Research Intern at Pramaana, you’ll contribute to one of several areas: model training, harness engineering, AI for Formal research or benchmark development. You’ll help run training experiments, investigate new approaches to symbolic reasoning, or build evaluation harnesses that help us measure and improve model performance.
What You'll DoRun model training experiments and analyze the results.
Design harnesses for auto-formalization and prover systems.
Build and maintain benchmarks to measure performance.
Investigate where models succeed or fail, and suggest improvements.
Work with researchers and engineers to turn findings into the next set of experiments.
A solid grasp of deep learning fundamentals and how to evaluate models.
The ability to run careful experiments, communicate findings clearly, and work well with a research team.
Technical depth in at least one area relevant to the role, such as model training, formal methods, or evaluation systems.
The initiative to make progress on open-ended problems with limited direction.
Close attention to detail in your code, data, and results.
A background in formal verification (Lean, Coq, or Isabelle)
Hands-on experience training or fine-tuning LLMs, including work on pretraining, supervised fine-tuning, or reinforcement learning.
A strong publication record in top-tier venues (NeurIPS, ICML, ICLR).
Skills Required
- Solid grasp of deep learning fundamentals and model evaluation
- Ability to run careful experiments and communicate findings clearly
- Ability to work effectively with a research team
- Technical depth in model training, formal methods, or evaluation systems
- Initiative to make progress on open-ended problems with limited direction
- Close attention to detail in code, data, and results
- Background in formal verification, such as Lean, Coq, or Isabelle
- Hands-on experience training or fine-tuning large language models
- Experience with pretraining, supervised fine-tuning, or reinforcement learning
- Strong publication record in top-tier venues such as NeurIPS, ICML, or ICLR
What We Do
Pramaana Labs builds the verification layer for AI, translating complex human knowledge—including tax codes, clinical guidelines, legal rules, and safety constraints—into machine-checkable logic. Its domain-specific systems use provers and solvers to search solution spaces and return proof artifacts, counterexamples, and traceable explanations for expert review. The aim is to make AI answers verifiable, challengeable, and defensible, supporting more accountable AI deployment across high-stakes applications.
