1 month ago
Berlin, GermanyMid Level
Responsibilities
- Design, train, and fine-tune machine learning models for autonomous driving use cases.
- Integrate trained models into production systems for reliable, efficient, and safe operation.
- Run structured experiments and evaluations using established metrics and benchmarks.
- Optimize models for latency, memory, and compute constraints in real-time autonomous systems.
- Collaborate with data, perception, and simulation teams to validate models against real-world scenarios.
Requirements
- Completed education in computer science, machine learning, data science, or a comparable field, or equivalent vocational training in a relevant technical discipline.
- At least 3 years of hands-on experience in applied AI/ML engineering.
- Strong knowledge of deep learning and reinforcement learning; familiarity with Active Inference is a plus.
- Strong Python skills, solid machine learning fundamentals, and hands-on experience with PyTorch and/or TensorFlow.
- Experience with reinforcement learning tools such as Stable-Baselines3 or RLlib and experiment-tracking tools such as MLflow or Weights & Biases.
- Experience deploying and optimizing models for production or real-time systems, including technologies such as ONNX, TensorRT, or C++ integration.
- Experience with Git, CI/CD pipelines, containerization, Docker, and ideally Kubernetes.
- Comfort working with cloud or GPU computing environments such as AWS, GCP, or Azure and data tools such as NumPy, Pandas, and SQL.
- Automotive industry experience, experience converting research papers into product features, and familiarity with CARLA or ROS/ROS2 are advantages.
- Valid driving license and English proficiency at C1 level; German is a plus.
Benefits
- Coverage of further education and training costs.
- Flexible working hours accommodating parenthood, caregiving, and voluntary work.
- Corporate Benefits partner discounts.
- Work on socially relevant autonomous-driving solutions.
- Public transport ticket subsidy.
- Attractive Berlin Wedding location with strong public transport connections.
- Face-to-face collaboration is emphasized; the company is not fully remote.
Tech Stack
Categories
