Software Engineer for Automotive AI Inference Stack (f/m/div)

Key responsibilities

• Design and implement high-performance inference runtimes for Infineon Automotive microcontrollers
• Integrate AI inference pipelines into embedded software stacks and real-time operating system environments
• Optimize models and runtime performance for latency, memory usage, power efficiency, and reliability
• Utilize MCU-specific acceleration capabilities and architecture-specific optimizations and implement highly efficient mathematical libraries for embedded inference
• Work closely with cross-functional teams including firmware, hardware, and algorithm engineers to ensure successful system integration
• Support maintainable deployment processes through version control, reproducibility, and traceability
• Evaluate and apply appropriate tools and frameworks for model conversion, quantization, and on-device inference
• Support strategic automotive customers during proof-of-concept and production phases and provide technical guidance on AI deployment best practices

Qualifications and Skills

• Self-driven engineer who takes ownership, adapts to evolving priorities, and consistently delivers high-quality results
• Combines technical excellence with a collaborative mindset and a commitment to customer success
• Bachelor's or Master's degree in Computer Science, Electrical Engineering, Embedded Systems, Computer Engineering, Software Engineering or a related technical field
• Expert-level C/C++ development, with strong debugging and problem-solving skills across software, AI model, and hardware integration layers
• Experience deploying AI/ML models to edge devices using frameworks and toolchains such as TensorFlow Lite Micro, ONNX, ExecuTorch, or similar, including model quantization, memory optimization, and performance tuning on constrained hardware
• Familiarity with sensor and signal processing workflows, including time-series data such as vibration, audio, current, or power signals
• Experience in automotive embedded applications, including exposure to ISO 26262, AUTOSAR, and MCU-based AI acceleration or edge inference platforms would be an advantage
• Knowledge of the AI deployment lifecycle, including model preparation, evaluation and conversion using Python-based ML tools, firmware release processes, and production validation would be an advantage
• Fluency in English