Description
About the role
Applied Intuition builds software infrastructure for autonomous vehicles across passenger cars, trucking, mining, and defence. Our Self-Driving Systems (SDS) team develops production-grade autonomy stacks deployed on real vehicles across multiple continents.
We are looking for an Engineering Manager to lead ML teams within SDS Core. This is a large organisation spanning perception model development, agent prediction, E2E driving models, ML engineering infrastructure, and the offboard training pipelines that power them.
Your teams will train models, iterate on architecture and data, run simulation and on-road experiments, and ship into production vehicles on timelines measured in months. The same model architecture must serve L2 ADAS, L4 trucking, and mining from a common codebase, while meeting the distinct safety and performance requirements of each.
At Applied Intuition, you will:
- Set the technical direction across multiple ML workstreams: the foundation model, shared backbone, and task heads that enable end-to-end driving, plus agent prediction and model optimisation.
- Lead rapid training and iteration cycles across your teams. Models ship into production vehicles on quarterly release cycles with direct impact on customer programmes.
- Work directly with OEM customers and programme teams to translate vehicle platform constraints into model architecture and delivery plans.
- Own the offboard ML pipelines that determine iteration speed: training infrastructure, data curation, autolabel quality, and the evaluation systems that connect offboard metrics to on-vehicle driving outcomes.
- Manage the full model lifecycle from prototype to embedded deployment, including training at scale, quantisation, and device-specific optimisations.
- Recruit, develop, and retain strong engineers in a competitive market.
We’re looking for someone who has:
- 5+ years in deep learning. Hands-on experience guiding teams in state-of-the-art ML development and deployment.
- 4+ years managing deeply technical product development teams
- Experience building ML training pipelines at scale: data management, distributed training, experiment tracking, model evaluation.
- Track record deploying ML models to embedded or edge hardware, including quantisation, pruning, and device-specific optimisations.
- Strong software engineering in Python and C++, comfortable across the full stack from training code to onboard inference.
Nice to have:
- Familiarity with occupancy-based scene representations, dense prediction heads, or sparse query-based architectures.
- Experience with closed-loop simulation for ML model evaluation (neural sim, log sim, scenario-based testing).
- Background in data flywheel design: automated ingestion, curation, quality monitoring, and dataset refresh workflows.
- Multi-domain ML development: training one model architecture across different sensor configs, vehicle types, or geographies.
- Experience at an AV company that has shipped autonomy to production.
Compensation at Applied Intuition for eligible roles includes base salary, equity, and benefits. Base salary is a single component of the total compensation package, which may also include equity in the form of options and/or restricted stock units, comprehensive health, dental, vision, life and disability insurance coverage, 401k retirement benefits with employer match, learning and wellness stipends, and paid time off.