Edge AI Engineer for Automotive Inference Systems

Infineon Technologies

Center City (MN)

On-site

USD 100,000 - 140,000

Full time

14 days+

Application generator

Turn this role into an interview — a resume and cover letter built around what this employer wants.

Get past ATS filters

Job summary

Infineon Technologies is seeking a Software Engineer for Automotive AI Inference Stack in our Research & Development team. You will merge creativity with your technical expertise by shaping the future of automotive AI and delivering high-performance inference on embedded platforms.

You will work across embedded software, AI deployment, and automotive applications to design runtimes, optimize latency and power, and collaborate with firmware, hardware, and algorithm engineers to ensure robust edge

Qualifications

Bachelor's or Master's degree in Computer Science, Electrical Engineering, Embedded Systems, or related field.
Expert-level C/C++ development with debugging across software, AI model, and hardware integration.
Experience deploying AI/ML models to edge devices using TF Lite Micro, ONNX, ExecuTorch, or similar.
Familiarity with sensor and signal processing workflows (time-series data).
Experience in automotive embedded applications, ISO 26262/AUTOSAR exposure is a plus.
Fluency in English.

Responsibilities

Design and implement high-performance inference runtimes for Infineon Automotive MCUs and integrate AI inference pipelines.
Optimize models and runtime performance for latency, memory usage, power efficiency, and reliability.
Utilize MCU-specific acceleration and architecture optimizations; implement efficient math libraries.
Collaborate with firmware, hardware, and algorithm engineers for system integration.
Support maintainable deployment processes with version control, reproducibility, and traceability.
Evaluate and apply tools/frameworks for model conversion, quantization, and on-device inference.
Support automotive customers during proof-of-concept and production phases with guidance on AI deployment.