Description:

Build and ship generative AI features end to end, from model selection to inference.
Design multi-agent and retrieval-augmented generation architectures, and anomaly detection systems.
Own the real-time inference layer on Triton and TensorRT, optimizing for latency and throughput.
Develop surrounding microservices in Python and FastAPI, ensuring reliability through containerization.
Set technical standards, make architecture decisions, and mentor other engineers.
Collaborate with research and product teams to transition ideas into dependable services.

Requirements:

5 to 10 years of relevant experience, with a proven track record as a technical lead.
Strong Python engineering skills with experience in production services (FastAPI or similar).
Hands-on experience with generative AI, including LLMs, RAG, and anomaly detection.
Real-time inference experience with NVIDIA Triton and TensorRT, focusing on performance metrics.
Familiarity with microservices architecture, Docker, Kubernetes, and large-scale distributed systems.
Right to work in the UK; open to applicants from all backgrounds.

Genuine build mandate within an established AI Core team, not just proof-of-concept work.
Fully remote working arrangement within the UK, focused on delivery.
Competitive salary and strong benefits with opportunities for career growth.
Support from C-Serv throughout the hiring process and beyond.
Values-led, woman-owned delivery partner emphasizing empathy, integrity, and collaboration.

Skills