Software Engineer (Planning & Evaluation)

Oxa · Oxford, England, United Kingdom
LinkedIn

Posted

Aug 11, 2026 (Aug 11)

Seniority

Not Specified

Work Model

Not Specified

Type

Not Specified

Category

Full-Stack

Salary

Not specified

Skills

Artificial Intelligence C++ GCP Generative AI Google Cloud Machine Learning MLOps Python

Description

Working at Oxa At Oxa, we're building the future of Industrial Mobile Autonomy (IMA) and are in the market for new talent. Oxa’s customers are the operators of some of the world's largest industrial facilities. Our technology transforms existing industrial vehicles into intelligent autonomous fleets, unlocking new levels of productivity, safety, and performance. ‘The phone in your hand, the coffee on your desk, the shirt on your back - they all moved through a web of ports (air and sea), distribution yards and manufacturing hubs. This is the invisible circulatory system of global trade, and it relies entirely on a relentless, repetitive shuffle of goods. Towing. This towing task happens in complex, commerce-critical industrial environments. Here, having self driving technology “do the driving” delivers immediate, measurable impact. IMA will revolutionise the movement of goods across the world's ports, airports, and yards. You can be part of that as an Oxbot’ ‘Paul Newman - Founder and CEO’ Our products are built on four core technology pillars which come together to build a complete system: Oxa Ware – Our modular autonomy hardware systems for consistent and repeatable integration of autonomy with existing vehicles. Oxa Driver – Our Physical AI, embodied in Oxa Ware, self-driving software that enables vehicles to perceive, reason, and drive autonomously in complex real-world environments. Oxa Foundry – Our development toolchain that leverages generative AI to continuously train and assure Oxa Driver, synthesising situations and sensor data. Oxa Hub – Our suite of cloud services for monitoring, managing and orchestrating fleets driven by Oxa Driver, including an API for integration with existing logistics systems . Behind these technologies is our exceptional team, the Oxbots . We are home to some of the world's leading experts in autonomous systems, robotics, machine learning, artificial intelligence, cloud infrastructure, and distributed software engineering. Together, we're solving some of the hardest technical challenges in autonomy, turning the research and development we do into production and deploying it into environments. Making robots do useful work. Your Role You will join a growing team of computer science and robotics experts bridging the gap between cutting-edge machine learning and production autonomy. Your work will focus on integrating ML-based reasoning models into the broader Oxa Driver™ planning and driving stack, whilst developing the simulation and metrics tools necessary for closed-loop evaluation and validation at scale. Key Responsibilities Integrate state-of-the-art machine learning (ML) based motion planning models (e.g., Behaviour Cloning, Reinforcement Learning) into the core planning and driving software stack, ensuring seamless interoperability and real-time performance. Develop and maintain driving simulation and scenario generation tools to stress-test planning behaviors against diverse, safety-critical edge cases. Design and execute closed-loop evaluation frameworks that quantify system-level performance and provide rapid feedback for model improvement. Bridge the sim-to-real gap between offline model training, virtual testing, and on-vehicle performance by instrumenting, monitoring, and analyzing model behavior within the simulation environment. Collaborate across teams to ensure that ML planning models respect the constraints and requirements of the full autonomy stack, including perception, mapping, and vehicle control. 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 Understanding of how ML models (particularly in motion planning) interact with broader autonomous driving software stacks. Hands-on experience with simulation frameworks, driving benchmarks, and closed-loop testing methodologies. Strong software engineering proficiency in Python with experience in system integration and building robust, maintainable tooling. Ability to design and interpret metrics that bridge the gap between simulation results and real-world safety/comfort performance. Experience in managing experiment cycles, from simulation to data-driven model iteration. Strong knowledge of trajectory tracking and optimization methods, used to score, evaluate, and refine trajectories generated by the ML Planner. 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.