Senior Machine Learning Engineer – Perception Team

About the role

As a Senior Machine Learning Engineer in the Perception team, you will own the end‑to‑end deep‑learning infrastructure that powers Bosch's L2+ ADAS stack. You will work at the intersection of cloud, on‑premise compute and data engineering to enable fast, reliable training of multimodal models.

Key responsibilities

• Manage and optimise the full DL infrastructure, including Azure Blob Storage, VNET setups and hybrid Cloud/On‑premise clusters.
• Lead performance benchmarking of next‑gen hardware (e.g., H200 vs H100) and Azure native deployments.
• Maintain and scale Kubernetes clusters for training and inference workloads.
• Design high‑performance data loaders for multimodal datasets (camera, radar, temporal data).
• Modernise data pipelines with Ray and Kubernetes to parallelise caching, shuffling and oversampling.
• Use PyArrow and SQL to optimise data consumption and implement delta‑based dataset updates.
• Build and maintain GitHub Workflows, CI pipelines and Grafana dashboards for compute usage, GPU efficiency and system health.
• Handle dependency updates such as PyTorch upgrades, Ubuntu patches, Hydra configuration and Dependabot maintenance.

Required profile

• Proven senior‑level experience delivering scalable deep‑learning infrastructure.
• Strong problem‑solving skills with a “T‑shaped” expertise in infrastructure, multitask deep learning and software design.
• Ability to work independently, think critically and drive projects to production.

Required skills

• Azure Blob Storage and VNET configuration
• Kubernetes (cluster management, training & inference)
• Ray for distributed data processing
• PyArrow and SQL for data handling
• GitHub Actions / CI‑CD pipelines
• Grafana for monitoring
• PyTorch (Torch) and GPU optimisation
• Ubuntu, Hydra, Dependabot