About Company
Founded in 2022, XG Tech is driving the future of smart vehicles. Its mission is to empower the digital transformation of automobiles, moving from distributed computing to a centralized, cross-domain platform.
XG Tech focuses on the intelligent cockpit—the next frontier of differentiation—while seamlessly integrating advanced driving systems. By reimagining cars as mobile living spaces, XG Tech aligns with the evolving trend of vehicles becoming the “third living space.”
Role Summary
As an Embedded AI Engineer, you will develop and optimize on-device AI systems for cloud–edge collaborative computing, integrating model routing, lightweight language models, and AI agent runtimes on embedded hardware. You will focus on improving inference performance, memory efficiency, power consumption, and system reliability, ensuring AI applications run efficiently, responsively, and securely on resource-constrained devices.
Key Responsibilities
- Own on-device integration of the model routing stack: runtime bring-up, memory and thermal budgets, model loading and switching, and fallback behaviour when the cloud is unavailable or slow.
- Co-design the device–cloud interface — what crosses the boundary, when, and with what guarantees — with the routing algorithm team, and push back when a design cannot survive real hardware.
- Profile and optimise end-to-end latency on real hardware; make the "local first" path genuinely fast rather than nominally fast, including cold start, steady state, and everything in between.
- Build the measurement harness that tells us what the device can sustain under load, and turn that into hard constraints the algorithms must respect.
- Own stability in the field: watchdog behaviour, recovery from bad states, and diagnostics that let us debug a device we do not have in front of us.
- Work with hardware and systems partners on deployment, update, and diagnostics, and be the person who can tell a vendor bug from ours.
How you will stand out
- Strong background in Embedded Systems, Computer Engineering, Computer Science, or a related field, with solid proficiency in C/C++ and low-level system debugging.
- Hands-on experience deploying and optimizing machine learning inference on resource-constrained devices, including NPU, DSP, or GPU acceleration.
- Strong understanding of model quantization, operator support, memory optimization, performance profiling, and power efficiency for on-device AI workloads.
- Demonstrated engineering capabilities through shipped hardware products, optimized inference runtimes or kernels, measurable performance improvements, open-source contributions, or technical competition achievements.
- Ability to bridge research and production engineering by translating AI models and research implementations into efficient, reliable, and deployable embedded solutions.
- Strong problem-solving and debugging skills, with the ability to identify performance bottlenecks and address real-world hardware and runtime constraints.
Nice to have:
- Familiarity with AI agent runtimes, on-device AI frameworks, or long-running embedded services.
- Experience working with heterogeneous SoCs, hardware accelerators, and vendor-specific development toolchains.
- Experience in privacy-preserving on-device inference or cloud–edge collaborative AI architectures.
XG Tech is committed to providing equal employment opportunities by country, state, and local laws. XG Tech does not discriminate against employees or applicants based on conditions such as race, color, gender identity and/or expression, sexual orientation, marital and/or parental status, religion, political opinion, nationality, ethnic background or social origin, social status, disability, age, indigenous status, and union.
You apply on MyCareersFuture, where this job was posted. Peter Nowak isn’t the employer and doesn’t check listings.
