Research Intern
Pramaana LabsPalo Alto, BengaluruOn-Site
Needs a free Superjobs account. You'll finish on Pramaana Labs's Ashby page.
Skill score
Summary
The research intern contributes to model training, harness engineering, AI for formal reasoning, or benchmark development at Pramaana Labs, running experiments, building evaluation harnesses, and turning findings into new experiments. The role suits candidates with deep learning and evaluation fundamentals who can work independently on open-ended problems.
- Estimated salary
- Est. ₹1.5–2.5 LPA
- Estimated for an internship, India. Not published by the employer.
- Work mode and location
- On-Site, Palo Alto, Bengaluru
- Employment type
- Internship
Job description
Overview
The Role
As 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.
Roles and responsibilities
- Run 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.
Skills required
Top skills
- Deep learning fundamentals
- Model evaluation
- Experiment design
- Symbolic reasoning
All skills (8)
- Formal methods
- Model training
- Evaluation harnesses
- Benchmark development
- Lean 4
- Coq
- Isabelle
- LLM fine-tuning
Qualifications
- 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.
Nice to have
- 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).
Company info
About Pramaana Labs
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.