R

Reasonable AI

Applied AI research for formal verification

Student Researcher Program Intern - Formal Reasoning, LLM Post-Training

AI ResearchUpdated on Nov 13
InternshipNo salary listed

About the Job

Requirements

  • Research students must be currently enrolled in a PhD or research master's program in Computer Science, Applied Mathematics, or a related technical field and return to the program after the internship.
  • Junior students must be currently enrolled in the early years of an undergraduate program or, in exceptional cases, high school, and demonstrate excellence in mathematics, programming, or AI, such as olympiad results.
  • Demonstrate expertise in a relevant computer science area, such as formal language processing, machine learning (especially large language models, reinforcement learning, or other post-training methods), algorithmic foundations of optimization, mathematical models of program semantics, programming language theory, design of distributed systems, or cybersecurity.
  • Show extracurricular interest in the intersection of machine learning, formal methods, and software engineering, even if current work does not address it.

Responsibilities

  • Take on a focused research project connected to the company's core work in machine learning and formal verification, with the project shaped upon arrival.
  • Run experiments producing results suitable for publication or open-sourcing, including training runs, verification benchmarks, theoretical work, or product development contributions.
  • Work alongside the technical staff in a mutual exchange of expertise and practical production and research experience.
  • Participate in technical conversations beyond the assigned project.
  • Work on-site alongside the founding technical team in Budapest or London.

Desired Qualifications

  • Have published at venues such as NeurIPS, ICML, ICLR, POPL, PLDI, CAV, or similar.
  • Have open-source contributions to relevant projects such as LEAN, Verus, Rocq, training frameworks, or similar.
  • Already be working at the intersection of machine learning and formal methods.

About the Company

Reasonable AI

Applied AI research for formal verification

Reasonable AI builds AI systems for formal verification of mission-critical software. It blends language models with formal methods to generate, repair, and verify machine-checkable proofs that accompany code, using Verus. They train small, specialized models that can match larger systems in proof accuracy while running faster, and analyze how models fail to prevent cheating. Their goal is to reduce the verification bottleneck from AI-assisted code, enabling engineers to produce software with formal correctness guarantees and machine-checkable proofs for each production line.

Company size
1-10
Company stage
Not listed
Total funding
Not listed
Headquarters
London, United Kingdom
Founded
2025

Recently Posted Jobs

Explore more opportunities at Reasonable AI

See more jobs