Applied AI Scientist, Simulation & Reinforcement Learning
Job description
Applied AI Scientist role at Locus Robotics owning the SimPy-based discrete-event simulator behind SDL, an RL-driven orchestration framework for people and robots, and growing into reinforcement learning work. The simulator is used to develop, tune and validate policies before deployment to live warehouses.
At a glance
- Employment
- Full-time · Employee (employment agreement)
- Work mode
- Remote · United Kingdom
- Languages
- English – fluent
- Pay
- GBP 70,000 – 120,000 / year
What you'll do
- Own and develop the SimPy-based discrete-event simulator, including its logic, design choices and fragile areas
- Pay down technical debt: improve test coverage, code quality, reproducibility and developer tooling
- Build experiment infrastructure around the simulator: orchestration, study management, reporting and automated runs across benchmark sites
- Generate and maintain site data (e.g. distance files, configs) needed to simulate customer warehouses
- Support scenario testing and sensitivity analysis for the order-engine and orchestration teams
- Define, measure and reduce the sim-to-real gap against real site data
- Run parameter optimisation and tuning studies (e.g. Optuna), and diagnose anomalies and non-determinism
- Model warehouse processes such as congestion, picker behaviour and queueing at the right level of fidelity
- Communicate results and confidence clearly to engineering, product and operations stakeholders
- Turn the simulator into a proper RL environment (Gymnasium/Gym-style interfaces) with fast, repeatable, scalable training runs
- Design, train and evaluate RL policies, starting with guidance generation, and benchmark them against current heuristic algorithms
- Guard against overfitting to simulator artefacts, and design experiments that show what transfers to the real world
- Prototype, evaluate and productionise learning-based components alongside the wider ML, MLOps and OE teams
- Stay current with RL, multi-agent systems and simulation research, and assess what is applicable to Locus
- Contribute to internal technical papers, patents and, where appropriate, publications
What we're looking for
- A PhD in Computer Science, AI/ML, Robotics, Mathematics, Physics, Operations Research or a related quantitative field, or MSc and 5+ years of industry experience applying AI/ML or simulation to real-world problems
- Hands-on experience building, extending or validating simulators, ideally discrete-event simulation (SimPy or similar)
- Practical experience with reinforcement learning and training simulation-based agents, including simulation for RL and Gym-style environments
- Strong Python and software engineering fundamentals: testing, code review, maintainable and reproducible code
- Rigorous experimental and statistical thinking: benchmarking, tuning, ablations, uncertainty
- Experience in robotics, logistics, warehouse or other operations-heavy domains
- Excellent English communication skills, both written and verbal, with the ability to engage diverse audiences effectively and explain uncertain results clearly to technical and non-technical audiences in a multidisciplinary environment
- Candidates must reside in the UK
- Candidates must have the legal right to work in the UK
Your team
Applied Data Science (ADS)
A small, collaborative team where research meets production; reporting to Oscar Mendez.
Benefits
- Bonus
- Equity
Apply
About Locus Robotics
AI-powered systems and intelligent robots that keep global supply chains running
Locus Robotics builds AI-powered systems and intelligent robots that keep global supply chains running. Its platform combines advanced AI, real-time decision-making, and autonomous robotics to help leading companies improve efficiency, scale operations, and adapt to constant change.
What they value
- Continuous learning
- Invest in our people
- Meaningful work with real-world impact