Expert Software Engineer - Edge AI

You will build and sustain the platform alongside Windriver team that runs AI Systems on the device— a Rust-based system that manages AI application lifecycles across a heterogeneous fleet of edgehardware.

This is hands-on work on hard systems problems: constrained compute, cross-architecture builds, OTA updates, and production-grade observability. You will have real infl uence over architecture andtechnical direction, and you are expected to make AI tooling a core part of how you work.

YOUR ROLE

• Design and implement the edge packaging and runtime system — a containerless / OCI-basedapproach to shipping AI Systems to heterogeneous devices
• Maintain the on-device orchestration platform (daemon, CLI, IPC, libraries), including OTA updateand lifecycle management for fielded devices
• Optimize inference and resource usage on constrained CPU/GPU/NPU hardware
• Harden cross-compilation and CI/CD pipelines for reproducible, secure multi-architecture builds
• Integrate the device fl eet with the cloud control plane and backend services (REST/gRPC, OpenAPI, MQTT)

Guide technical direction for core platform componentsUse agentic AI coding tools daily for implementation, refactoring, review, and debugging, withreal judgment about where they help and where they don'tRaise the team's AI-assisted engineering practice: working patterns, guardrails, and what stayshuman-owned

• Building AI culture inside and outside of teamKeep the codebase and its documentation in a state that people can work in effectively
• YOUR BACKGROUND
• Degree in Computer Science, Machine Learning, or a related fi eld, with 3+ years of software engineering experience including 2+ years in embedded Linux or systems programming
• Production proficiency in Rust or Python (C/C++ for native libraries and low-level device code is a plus)

Hands-on experience using agentic AI tools in the software development workflow— AI coding assistants and agents for implementation, refactoring, and review — and a clear point of view on their limitsLow-level fundamentals: memory, concurrency, the build/link toolchain, and how software actually runs on constrained hardware

Experience with PyTorch, TensorFlow Lite, ONNX, or TensorRT.

Strong debugging and problem-solving on complex, distributed systems

• Effective in a team distributed across the US, Europe, and IndiaBroad range across the stack, including cloud, edge and web/backend development
• Understanding of networking stackNice to have:an ML inference runtime (ONNX, TensorRT, TF
• Lite, OpenVINO) and the practicalrealities of running models on-device; hardware-accelerated inference on NPUs/GPUs (Jetson, Qualcomm, Hailo, Ambarella); GenAI/LLM tooling, RAG pipelines, or ML infrastructure; multi-arch andembedded Linux builds (Yocto); a major cloud provider (AWS, GCP, Azure); GitLab CI
• Why join us?

You can grow at Aptiv. Aptiv provides an inclusive work environment where all individuals can grow and develop, regardless of gender, ethnicity or beliefs.

You can have an impact. Safety is a core Aptiv value; we want a safer world for us and our children, one with: Zero fatalities, Zero injuries, Zero accidents.

You have support. We ensure you have the resources and support you need to take care of your family and your physical and mental health with a competitive health insurance package.

Your Benefits at Aptiv:

Private health care (Signal Iduna) and Life insurance for you and your beloved onesWell-Being Program that includes regular webinars, workshops, and networking events

Hybrid work (min. 47 days/yr of remote work, flexible working hours)

Employee Pension Plan paid by the employer (you get + 3,5% on each gross salary.

Access to sports groups and Multisport cardApply today, and together let’s change tomorrow!