Senior Member of Technical Staff (Inference Acceleration & Agent Framework / RSI)

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 AI Systems Research Engineer, you will research and develop efficient AI inference systems and adaptive agent frameworks for personal AI computers. You will optimize model serving, inference performance, and resource utilization to enable AI agents to operate continuously with low latency and cost on local hardware. You will also design and improve agent runtimes, execution frameworks, and self-improving systems that learn from usage and continuously optimize their performance, reliability, and efficiency over time.

Key Responsibilities

Inference acceleration

• Own inference performance for the models we deploy: kernels, batching, cache management, quantization, speculative decoding, and the profiling that tells you which of those actually matters.
• Cut latency and cost without giving up quality, and prove it with measurements rather than estimates.
• Work with the routing and embedded teams so that serving decisions reflect what the hardware can really sustain, including the thermal and power envelope.

Agent framework and recursive self-improvement

• Build and evolve the agent harness: how tasks are decomposed, how tools and models are called, how traces are captured, replayed, and analysed.
• Work on self-improvement honestly: which experience is worth keeping, how to judge it without self-flattery, and how to turn it into a policy change that generalises instead of memorising.
• Treat evaluation as part of the loop — a harness change that is not measured is not an improvement, and a score that went up for the wrong reason is a regression.
• Keep the framework usable: the people running experiments on top of it should not have to read your internals to do their job.

How you will stand out

• Strong academic background in Computer Science, Systems Engineering, Machine Learning, or a related field, with a PhD or equivalent research experience preferred
• Hands-on experience in AI inference optimization, model serving, or distributed systems, particularly in improving inference speed, resource efficiency, and operational reliability.
• Strong systems engineering skills, including performance profiling, low-level optimization, memory management, and identifying system bottlenecks.
• Experience developing AI agent frameworks, execution runtimes, or self-improving systems, with an understanding of how agents can learn and improve through usage and interaction.
• Ability to design and implement rigorous evaluation frameworks to measure improvements in agent performance, reliability, and efficiency through systematic experimentation.
• Demonstrated research or engineering achievements through publications in efficient inference, AI agents, or self-improving systems, as well as production inference systems, open-source frameworks, technical competitions, or products with active users.
• Strong analytical and problem-solving skills, with the ability to evaluate optimization trade-offs and distinguish measurable performance improvements from marginal or unsustainable gains.

Nice to have:

• Experience with speculative decoding, KV-cache optimization, custom GPU kernels, or inference acceleration techniques.
• Experience developing AI agent harnesses, tool-use frameworks, or trace-based learning systems.
• Familiarity with deploying and optimizing AI inference on local hardware under constrained compute, memory, and power budgets.
• Experience with continuous learning, self-improving agents, or automated optimization of agent workflows.

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.