Senior RL Research Engineer

London

See advert for pay

About Recurvia

Recurvia is a frontier reinforcement learning lab building AI systems that improve other AI systems.

Our mission is to accelerate machine learning development using machine learning itself. Our work spans fundamental reinforcement learning research, large-scale experimentation, and product development.

Our current products are the first applications of this research programme:

Paramorph - a foundation model, trained with multi-agent reinforcement learning, that controls and optimises the training of other AI models.
Metrana - an AI-powered observability platform for large-scale reinforcement learning and foundation model training workloads.

We are backed by Amadeus Capital Partners, the European Innovation Council and Amazon Web Services. Following the award of a €2.5 million EIC Accelerator grant, we are expanding the team to accelerate development and commercialisation of our technology platform.

About the Role

We are looking for an exceptional Senior Reinforcement Learning Research Engineer to join our research team.

You will play a central role in developing Paramorph and the next generation of reinforcement learning technologies emerging from Recurvia's research programme. Working at the intersection of research and engineering, you will design and evaluate novel RL algorithms, run large-scale experiments, and turn promising research into robust, production-ready systems.

The role suits someone who combines deep technical expertise with scientific curiosity: developing new approaches to hard problems in reinforcement learning, optimisation and foundation model training; analysing experimental results; and iterating rapidly to improve performance.

You will work closely with research scientists and engineers across the company, shaping both the scientific direction of our work and the systems built from it. This is an opportunity to join a deep reinforcement learning lab at an early stage and help build technology that could change how AI systems are trained and optimised.

Key Responsibilities

Design, implement and evaluate novel multi-agent reinforcement learning algorithms for optimising AI training and inference.
Plan, execute and analyse large-scale experimental campaigns to validate and improve algorithmic performance.
Work closely with research scientists to translate new ideas into robust, scalable systems.
Contribute to the company's scientific direction through experimentation, analysis and technical discussion.
Improve the performance, reliability and scalability of our reinforcement learning systems.
Collaborate with engineers across the company to integrate new technologies into production environments.

Required Skills & Experience

MSc, PhD or equivalent industry experience in computer science, machine learning, AI or a related discipline.
Strong practical experience developing and evaluating multi-agent reinforcement learning systems.
Deep understanding of reinforcement learning theory and modern machine learning techniques.
Excellent Python skills and experience building production-quality software.
Strong experience with PyTorch and the modern machine learning ecosystem.
Ability to drive research and engineering projects independently, from concept through evaluation.

Desirable Skills & Experience

Experience training, fine-tuning or optimising foundation models.
Experience with large-scale distributed training and experimentation.
Experience with JAX, CUDA or other high-performance ML tooling.
Publications at leading machine learning conferences or journals.
Contributions to open-source machine learning or reinforcement learning projects.
Experience in a research-driven environment such as a frontier AI lab, advanced AI startup or leading academic group.

What We Offer Competitive Compensation

Competitive salary and meaningful equity participation.

Frontier AI Research

Work on novel reinforcement learning technologies with the potential to influence how future AI systems are trained and optimised.
Substantial compute resources and the freedom to pursue ambitious experimental research. Research Impact
Support for publication at leading venues such as NeurIPS, ICML and ICLR, where appropriate.
Opportunities to contribute to patents, open-source projects and novel technological advances.

Join at a Pivotal Stage