Senior ADAS & Embedded Integration Engineer

A company is developing next-generation conversational driving experiences that combine Vision Language Models (VLMs) with advanced driver assistance systems. As part of a lean, highly technical team, the Senior ADAS & Embedded Integration Engineer will be responsible for integrating AI-based perception and reasoning capabilities into an existing parking system and deploying them on automotive-grade hardware.

The role involves working at the intersection of embedded software, ADAS systems, AI deployment, and vehicle integration. The engineer's work will enable natural language parking interactions while ensuring reliable operation within the constraints of automotive platforms.

Key responsibilities:

• Integrate VLM-based components into an existing parking and ADAS software stack.
• Design and implement interfaces between AI components, perception systems, and parking functions.
• Deploy and optimize AI models on automotive compute platforms.
• Develop software for sensor, camera, and vehicle-system integration.
• Evaluate runtime performance, memory usage, and latency of AI workloads.
• Support simulation, HiL, and vehicle-level testing activities.
• Collaborate with ML engineers to transition research prototypes into robust software components.
• Identify integration risks and drive resolution of complex technical issues.
• Contribute to software architecture and technical design decisions across the project.
• Help establish reusable patterns for future AI-enabled ADAS applications.

• Bachelor's or Master's degree in Computer Science, Electrical Engineering, Robotics, or related field.
• 3+ years of experience developing software for automotive, robotics, embedded, or real-time systems.
• Strong programming skills in C++ and Python.
• Experience developing software on Linux-based platforms.
• Experience working with ADAS, perception, robotics, or autonomous systems.
• Experience integrating complex software components across multiple subsystems.

Preferred qualifications:

• Experience with parking systems, low-speed maneuvering functions, or ADAS architectures.
• Experience deploying machine learning models using ONNX Runtime, TensorRT, or similar frameworks.
• Familiarity with automotive middleware and communication frameworks (ROS/QNX).
• Experience with NVIDIA DRIVE, Snapdragon Ride, or similar automotive compute platforms.
• Understanding of computer vision and machine learning concepts. Experience with simulation and vehicle validation environments.