Lead architect for production LLM-powered in-vehicle assistant backend system.
Design and own the architecture of a live, distributed backend service powering an AI-driven voice assistant across vehicle fleets. You'll manage the interface layer between vehicles and cloud services, implement streaming AI pipelines with LLM orchestration, and ensure high availability (99.5% SLO) while maintaining backward compatibility across multiple vehicle generations. This is a hands-on technical leadership role requiring deep expertise in Python microservices, cloud infrastructure on Azure, and production LLM systems.
Found at a specialist agency · listed 10 October 2026 · InsideJobs links you to the original posting.