Senior GenAI Platform Engineer: Inference & Tuning

Deliveroo; Greater London; Presencial; GBP 110 000 - 170 000; Tempo integral

Resumo da oferta

Deliveroo is seeking a Senior Software Engineer for its GenAI Platform to lead the design and architecture of production infrastructure powering GenAI products across teams. You will own open-weights serving, inference engines, and training pipelines, while guiding teams on cost/performance tradeoffs in a fast-evolving AI landscape.

The role requires a strong academic background (BSc/MSc/PhD in CS) and experience with LLM inference engines in production.

Qualificações

• PhD, MSc or BSc in Computer Science or equivalent.
• Experience with GenAI infrastructure and production-grade ML systems is a plus.
• Strong knowledge of open-weights model serving and inference architectures.

Responsabilidades

• Lead design of infrastructure to move GenAI ideas from prototype to production, boosting AI's business impact.
• Own and evolve open-weights serving stack, including real-time GPU endpoints, high-throughput batch inference, and fine-tuning pipelines.

Conhecimentos

Open-weights serving

GPU inference

Model training pipelines

Formação académica

BSc/MSc/PhD in CS

Ferramentas

vLLM

TensorRT-LLM

Descrição da oferta de emprego

Deliveroo is seeking a Senior Software Engineer for its GenAI Platform to lead the design and architecture of production infrastructure powering GenAI products across teams. You will own open-weights serving, inference engines, and training pipelines, while guiding teams on cost/performance tradeoffs in a fast-evolving AI landscape.

The role requires a strong academic background (BSc/MSc/PhD in CS) and experience with LLM inference engines in production.