Senior GenAI Infra Engineer: Open-Weights & GPU Inference

Docwrite; Greater London; On-site; GBP 110,000 - 180,000; Full time

Job summary

Deliveroo is looking for a Senior Software Engineer to own the GenAI infrastructure, spanning real-time serving, high-throughput batch inference, and model fine-tuning. You will set technical direction for open-weight platforms and collaborate across DoorDash, Wolt, and Deliveroo teams to accelerate AI-powered products.

You will lead design decisions, mentor engineers, and drive production readiness with observability, latency, and cost controls as core priorities.

Qualifications

• BSc, MSc or PhD in Computer Science or equivalent.
• 5+ years of industry experience in software engineering.
• Deep backend engineering fundamentals, especially in Python and distributed systems.
• Track record of designing and owning production services, APIs, data pipelines, or ML infrastructure at scale.
• Experience operating systems in production, including observability, debugging, reliability, incident response, and performance/cost optimization.
• Hands-on experience with LLM inference and/or fine-tuning of open-weight models in production.
• Demonstrated technical leadership: leading design across ambiguous areas and mentoring engineers.
• Proficiency in using AI coding tools in the full SDLC.

Responsibilities

• Lead the design of infrastructure that moves GenAI ideas from prototype to production and increases business impact.
• Own and evolve the open-weights serving stack, real-time endpoints, batch inference, and fine-tuning.
• Architect scalable systems for model serving, batch inference, GPU autoscaling, and fine-tuning for real-world use cases.
• Push cost and latency frontiers while ensuring reliability, observability, and controllable costs.
• Build platforms that support rapid experimentation while meeting production standards for latency and scale.
• Partner with ML engineers, product engineers, data scientists, and platform teams to turn GenAI capabilities into durable primitives.
• Set technical direction for the centralised GenAI platform including RLHF/RLVR and agentic techniques.

Skills

Python

Distributed systems

LLM inference

Production services

Observability

Technical leadership

AI coding tools

Education

BSc/MSc/PhD in Computer Science or equivalent

Tools

Kubernetes

AWS

GCP

Job description

Deliveroo is looking for a Senior Software Engineer to own the GenAI infrastructure, spanning real-time serving, high-throughput batch inference, and model fine-tuning. You will set technical direction for open-weight platforms and collaborate across DoorDash, Wolt, and Deliveroo teams to accelerate AI-powered products.

You will lead design decisions, mentor engineers, and drive production readiness with observability, latency, and cost controls as core priorities.