Opportunity at
DeliverooSenior Software Engineer, GenAI Platform
This is a full-time, on-site Senior Software Engineer role in London on the GenAI Platform team, part of Machine Learning Platform. The team develops shared infrastructure…
Career Tools
About This Role
This is a full-time, on-site Senior Software Engineer role in London on the GenAI Platform team, part of Machine Learning Platform. The team develops shared infrastructure that allows Deliveroo, DoorDash and Wolt to take generative AI products, agents, automation and personalisation into production in a controlled way. The aim is to speed up the business value that GenAI delivers. A large share of the work is running open-weight large language…
Job Description
This is a full-time, on-site Senior Software Engineer role in London on the GenAI Platform team, part of Machine Learning Platform. The team develops shared infrastructure that allows Deliveroo, DoorDash and Wolt to take generative AI products, agents, automation and personalisation into production in a controlled way. The aim is to speed up the business value that GenAI delivers.
A large share of the work is running open-weight large language and vision-language models in-house, among them GLM, Qwen, Kimi and DeepSeek. This covers live GPU endpoints, large offline inference runs and model tuning on GPUs that scale with demand. The posting reports significant reductions in cost and latency from this approach. The team also maintains core platform pieces, including an LLM gateway, an agent gateway, evaluation tooling, guardrails and cost attribution.
The engineer leads the design of the open-weights model platform across inference and fine-tuning, and sets technical direction for serving engines, training pipelines, GPU scaling, batch systems, backend services and observability. Mentoring engineers and collaborating with teams across all three companies is part of the role. Directions the posting names for later include reinforcement learning and agent optimisation.
The role suits a senior engineer who is at ease owning ambiguous, high-stakes systems and who wants to push the cost and performance of GPU inference further. A minimum of five years in software engineering is needed, with strong backend and distributed-systems skill in Python and production experience serving or fine-tuning open-weight models. Technical leadership and fluency with AI coding tools across the whole development cycle are also expected.
Responsibilities
- Lead the design and architecture of the open-weights model platform for inference and fine-tuning.
- Own real-time GPU serving, batch inference and fine-tuning services.
- Bring down the cost and latency of GPU inference and let product teams choose between open and closed models.
- Build platforms that allow fast experimentation while meeting standards for latency, scale, monitoring and SLOs.
- Set technical direction for the centralised GenAI platform.
- Mentor engineers and work alongside ML, product, data science and platform teams.
Requirements
- A bachelor's, master's or doctoral degree in computer science, or an equivalent qualification.
- At least five years of industry software engineering experience.
- Strong backend foundations, particularly in Python and in distributed design.
- Hands-on record of operating APIs, data pipelines, ML infrastructure and production services at real scale.
- Experience running production systems, including observability, incident response and cost control.
- Hands-on experience serving or fine-tuning open-weight LLMs in production.
- Demonstrated technical leadership in ambiguous, fast-changing areas.
- Proficiency with AI coding tools across design, coding, testing and release.
Qualifications
- Experience with inference engines such as vLLM, SGLang or TensorRT-LLM.
- Experience with distributed fine-tuning and training pipelines, such as SFT, DPO, RLHF or LoRA.
- GPU performance work, such as multi-node inference, memory tuning or quantisation.
- Experience with Kubernetes, AWS, GCP or elastic GPU platforms.
- LLM gateway or model routing know-how, and cost attribution work.
- Experience building developer or internal platforms.
- Hands-on work shipping AI agents or MCP servers into live use.
- Experience with evaluation systems, LLM observability, RAG or vector databases.
Core Skills
Frequently Asked Questions
Answers are based only on the employer’s listing; where it doesn’t say, neither do we.
Where is this role based?
The role is based in London and is listed as on site.
What type of employment is offered?
This is a full-time position.
What experience is required?
A bachelor's, master's or doctoral degree in computer science, or equivalent, and at least five years of industry software engineering experience are required.
Is a salary stated in the posting?
The posting does not state a salary or benefits.
Sample Interview Questions
AI-generated questions tailored to this specific role — a preview of the full practice set.