Your Team

You will join a growing team of computer science and robotics experts leveraging machine learning, data and cloud infrastructure to build and deploy powerful on-vehicle reasoning capabilities. Your work will enable Oxa Driver™ to plan and execute sophisticated, safe driving behaviours scalebly across all of our customer domains.

As a Senior Engineer (ML Reasoning) you will be taking a leading role within research and development of your team to enable Oxa Driver’s data driven reasoning capabilities. You will actively be training, evaluating, and deploying state-of-the-art machine learning models to reason and plan how to drive in industrial environments.

Key Responsibilities

• Researching, developing, and deploying state-of-the-art machine learning models for autonomous vehicle trajectory planning, specifically utilizing Machine Learning techniques such as Behaviour Cloning (BC) and Reinforcement Learning (RL).
• Designing and scaling end-to-end pipelines for large-scale model training, ensuring efficient distributed training performance across simulation and real-world datasets.
• Applying strong experiment and data analysis skills to rigorously evaluate model performance, turn results into actionable items, and communicate findings with your team.
• Developing simulation-in-the-loop training and evaluation environments, defining rigorous safety/comfort metrics and test scenarios for planning performance analysis.
• Keeping up with the latest advances in imitation learning, deep reinforcement learning, and motion planning research, and applying relevant techniques to Oxa Driver.
• Optimising ML models and codebases for compute and memory efficiency to ensure efficiency in model training pipelines and meet vehicle deployment constraints.
• Understanding what data is needed to train and evaluate ML-based trajectory planning, and working with data teams and tools to source or generate the necessary real or synthetic data to achieve the team’s goals.
• You will be encouraged to share your ideas with the team and the wider business.
• You will interact with other teams to learn about the autonomy system and gain exposure to all aspects of the business.

What You Need To Succeed

• Machine Learning skills for motion planning and behaviour learning.
• A strong understanding of Behaviour Cloning and/or Reinforcement Learning or similar ML techniques.
• Experience with Machine Learning in a research environment.
• Demonstrate proficiency in Python software development skills.
• Strong analytical skills with a structured approach to experiment tracking, model evaluation, and metrics definitions.
• Ability to communicate your technical ideas and experimental results with colleagues.
• An ability to understand both technical and commercial requirements.

Extra Kudos If You Have

• Familiarity with cloud platforms, preferably Google Cloud Platform (GCP)
• Experience with MLOps
• Experience working with driving simulators, autonomous driving software, or traffic modelling
• Familiarity with C or C++

Your Interview Experience

Our interview process is designed to give you every chance to get the measure of us, and us of you. You will join three stages which will give you every opportunity to show your strengths and qualities, via scenario based questions and technical exercises.

What We Offer

• Competitive salary benchmarked against the market
• Participation in a great company equity scheme
• Enhanced pension contributions
• Annual holiday allowance of 25 days per year
• Overseas working policy for up to 8 weeks per year
• Flexible, hybrid and remote working arrangements
• Comprehensive Private Health cover with the option to add family members,
• Enhanced health and wellbeing benefits including health cash plan, critical illness cover, life assurance and group income protection
• Enhanced paid maternity and paternity policy

If you're excited by deep technical problems, real-world AI, and the opportunity to build technology that will reshape global industry, you'll find both the challenge and the impact you're looking for at Oxa.