Senior Software Engineer – ADAS

Senior Software Engineer – ADAS

Nvidia

Munich, Germany

We’re hiring a mid‑level Software Engineer to develop production ADAS and autonomous driving functions in C++ and Python. If you’re passionate about building robust, high‑performance features that run on GPUs in real vehicles, we’d like to hear from you.

What you’ll be doing:

• Design, implement, and maintain C++ ADAS functions for perception, prediction, and planning (e.g., lane keeping, ACC, AEB, traffic‑light and object handling) in a safety‑critical codebase;
• Integrate deep learning models into C++ pipelines: take models trained in Python (PyTorch or TensorFlow), export/convert them, and deploy them for real‑time inference on NVIDIA GPUs;
• Work with multi‑sensor data — cameras, radar, lidar — and implement sensor fusion, tracking, and decision‑making logic in C++;
• Build and extend testable, modular libraries and components, including interfaces to models, sensor drivers, and vehicle control;
• Profile, debug, and optimize C++ and CUDA code to meet strict latency and throughput targets;
• Contribute to tooling around data quality, automated evaluation, and regression tests for ADAS functions;
• Collaborate closely with ML researchers, systems engineers, and automotive partners to turn prototype algorithms into production‑ready C++ implementations.

What we need to see:

• 4–8 years of professional software engineering experience, ideally in ADAS, automotive, robotics, or real‑time systems;
• Master’s or PhD degree in Computer Science or in Machine Learning;
• Strong modern C++ (C++14/17 or later): templates, RAII, smart pointers, STL, and experience building large codebases;
• Solid Python skills for tooling, training scripts, and glue code between data pipelines and C++ components;
• Hands‑on experience training and using deep learning models (PyTorch or TensorFlow): designing experiments, tuning hyperparameters, working with large datasets, and debugging model behavior;
• Experience developing on Linux: build systems (CMake), debugging (gdb, sanitizers), profiling, and git‑based workflows in a CI/CD environment;
• Familiarity with one or more of:
  • - GPU programming and optimization (CUDA, TensorRT, cuDNN);
  • - Computer vision / perception (object detection, segmentation, multi‑object tracking);
  • - Robotics or autonomous systems (ROS/ROS2, ADAS features, simulation environments).

Ways to stand out from the crowd:

• Direct experience implementing ADAS functions in C++, such as lane keeping, adaptive cruise control, automatic emergency braking, or traffic‑sign/traffic‑light handling;
• Experience with camera calibration, sensor fusion, or multi‑camera perception systems;
• Knowledge of model optimization and deployment: quantization (INT8, FP8, 4‑bit), TensorRT‑LLM, ONNX Runtime, or similar frameworks;
• Background in training infrastructure: distributed training, experiment tracking, dataset versioning, hyperparameter optimization;
• Understanding of software quality practices for safety‑critical systems (code review, unit testing, static analysis; automotive standards knowledge is a plus) as well as open‑source contributions or published work in AI, robotics, or GPU computing.