Reasonable is the applied AI research company building formal verification for super-human software development. 

Correctness guarantees for software developed by humans and machines are no longer impractical or prohibitively expensive. Code generated by AI can be provably correct, rather than plausibly functional. At Reasonable, we are doing the research, training the models, and developing the products required to make this a reality. Achieving this creates a new paradigm for high accountability software development and unlocks the full potential of AI for professional engineers. 

We’re a compact, talent-dense technical team, with deep domain expertise in machine learning, formal verification and mathematical models of program semantics. Join us to develop the next frontier of formal reasoning and software engineering. Proof follows function.

We are seeking a highly motivated and skilled Member of Technical Staff specialized in Post-Training and Evaluations to join our Reinforcement Learning & Formal Methods team. The successful candidate will play a key role in advancing verifiable reasoning by designing and improving our fine-tuning pipeline.

Requirements

We're looking for

• Design and improve our SFT and RL training and evaluation pipeline for formal verification of software.
• Collaborate with formal verification experts and AI researchers to integrate RL techniques with formal methods.
• Track latest work in RL, post-training, formal verification, and bring the best ideas into our training and eval stack.

Must have skills

• Solid Python - PyTorch knowledge (or other frameworks) and debugging skills, familiarity with distributed training, and inference - serving engines, such as vLLM.
• Hands-on experience fine-tuning LLMs, including at least one RL method such as GRPO or PPO.
• Experience with GPU cluster usage.
• 2+ years of industry experience in AI/ML role.

Nice to have skills

• Proven track record of high-quality software contributions.
• PhD in Machine Learning, Computer Science, or related field.
• Capability to fast learning and adaption of formal verification related technologies and ideas.

Benefits

• Compensation: Generous salary, with equity and additional benefits
• Location: Budapest- Hungary or London-UK with flexibility for team and conference travel
• World-class team and environment: an opportunity to build alongside deeply experienced founders, in a well-funded company that’s backed by industry leading VCs and angels including Oriol Vinyals, Zoubin Ghahramani, Jonathan Frankle and Guy Podjarny, amongst many others