Pramaana Labs
Research Intern
Palo Alto +1 · On-site · Internship · Posted Sep 23, 2026
- Location
- Palo Alto
Bengaluru
About the job
Conduct research across model training, harness engineering, AI for Formal, or benchmark development to improve AI systems’ symbolic reasoning and evaluation.
What you'll do
- Run model-training experiments, analyze results, and investigate model strengths and failures.
- Design harnesses for auto-formalization and prover systems, and build and maintain benchmarks.
- Collaborate with researchers and engineers to turn findings into further experiments and improvements.
What they ask for
- Solid grasp of deep learning fundamentals and model evaluation.
- Ability to run careful experiments, communicate findings clearly, and work well with a research team.
- Technical depth in at least one relevant area: model training, formal methods, or evaluation systems.
- Initiative on open-ended problems with limited direction, and close attention to detail.
Nice to have
- Background in formal verification, such as Lean, Coq, or Isabelle.
- Hands-on LLM training or fine-tuning experience, or a strong publication record in NeurIPS, ICML, or ICLR.
Tools
Lean 4, Lean, Coq, Isabelle, NeurIPS, ICML, ICLR
AI focus
Research and experimentation to improve AI model training, symbolic reasoning, auto-formalization, prover systems, and model evaluation.
Model-written summary · the original posting is authoritative