Public summary
Join a pioneering technology team developing real-time ML infrastructure for automotive LiDAR perception software used in safety-critical embedded systems. Lead the technical direction of ML pipelines, focusing on end-to-end training, model optimization, and deployment to edge devices. Collaborate cross-functionally to enhance platform capabilities for ML engineers in a dynamic environment leveraging modern tools and languages.
Location and work setup
- Location
- Hamburg
- Remote status
- On-site
- German requirement signal
- No German Required Detected
- Detected job language
- English
Responsibilities
Lead design and development of the on-premises ML training pipeline covering full lifecycle management. Optimize models through pruning and quantization for deployment on embedded hardware in real-time LiDAR applications. Evaluate and benchmark models on servers and target devices. Build self-service platform capabilities to empower ML engineers for independent deployment while ensuring reliability and observability.
Qualifications
3+ years experience in MLOps or ML pipeline engineering with production ownership. Proven expertise in building ML training pipelines and model registries for edge devices. Strong understanding of throughput, latency trade-offs, and GPU resource management. Ownership mindset focused on delivering solutions. Platform engineering mindset prioritizing developer experience, documentation quality, reliability, and observability. Fluent in English; German language skills are a plus.