About the Role
Work on the infrastructure and systems required for improving the performance of machine learning models deployed across a fleet of vehicles in operational environments. You will architect systems to handle large datasets, potentially including images or videos, and work across the full stack, learning new areas as needed.
Responsibilities
- Build out the infrastructure required to improve the performance of machine learning models, including dataset curation/labelling, training, evaluation and deployment.
- Ensure model performance is constantly improving, whether that involves building the pipelines to collect operational data, supervising annotation/labelling, generating synthetic data, training models or optimising inference.
Requirements
- Experience with machine learning pipelines, from datasets through to evaluation and deployment (ML Ops)
- Experience with Python
- A solid grounding in backend development
- Experience with handling large datasets (computer vision or otherwise)
- Experience with deep neural nets
- Experience with computer vision
- Experience deploying ML models on edge
- Interest in working with unmanned aircraft
Skills
- Python
- Backend development
- Machine learning pipelines
- ML Ops
- Large datasets
- Deep neural nets
- Computer vision
- Deploying ML models on edge
Location
- UK
Work Type
- Remote
- Onsite
Experience Level
- Mid-level
Benefits
- Share options vesting over three years
- Bupa private health, fully funded from day one
- 6% employer pension contribution
- 25 days leave plus bank holidays
- Properly enhanced cover for both parents
- Enterprise level AI tooling, with as many tokens as you need
- Relocation support
- Home office budget
About the Company
- Minerva Defence is one of the fastest-growing defence technology companies in Europe.
- We create the software, hardware and networking that make unmanned systems effective on the modern battlefield, all ideated, designed and manufactured end-to-end in the UK, and in active use today.
- We are deliberately low-profile: a team of around 60, small in headcount and outsized in effect.
- We look for people who are not just talented but genuinely committed to the work, the team, and the purpose behind it.
