Impress employers and recruiters.
Choose from hundreds of resume examples.

Target Resume Now

About the Role

Join a high-leverage team building production infrastructure for Generative AI at Deliveroo and DoorDash, focusing on open-weights model platforms for inference and fine-tuning. You will work across model serving, inference engines, fine-tuning pipelines, GPU autoscaling, backend services, and observability. This role is for an engineer passionate about optimizing GPU inference and fine-tuning in a rapidly evolving technical landscape.

Responsibilities

Build infrastructure to move GenAI ideas from prototype to production, increasing AI business impact velocity.
Work on the open-weights serving stack, including real-time GPU endpoints, high-throughput batch inference, fine-tuning, LLM Gateway, Agent Gateway, evals infrastructure, guardrails, and cost attribution.
Design scalable, high-performance systems for model serving, batch inference, GPU autoscaling, and fine-tuning.
Optimize the cost and latency of GPU inference, transforming batch jobs and reducing inference costs.
Provide product teams with reliable choices across open-weight and closed-source models, including fallback, observability, and cost controls.
Build platforms that support rapid experimentation while meeting production standards for latency, scale, monitoring, SLOs, playbooks, and operational excellence.
Collaborate with ML engineers, product engineers, data scientists, and platform teams to integrate GenAI capabilities into durable platform primitives.
Shape the future of the centralized GenAI platform, exploring directions like reinforcement learning, agent optimization, and other advanced techniques.

Requirements

BSc, MSc, or PhD in Computer Science or equivalent.
3+ years of industry experience in software engineering.
Strong backend engineering fundamentals, particularly in Python and distributed systems.
Experience building 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 (serving and/or fine-tuning).
Ability to navigate ambiguous, fast-moving technical areas and translate customer use cases into reusable platform capabilities.
Proficiency in using AI coding tools (e.g., Claude Code, Codex, Cursor) throughout the software development lifecycle.

Skills

Python
Distributed systems
Production services
APIs
Data pipelines
ML infrastructure
Observability
Debugging
Reliability
Incident response
Performance optimization
Cost optimization
LLM inference
LLM fine-tuning
Open-weight models
GPU serving
Batch inference
Model fine-tuning
SFT
DPO
LoRA
AI coding tools

Location

Deliveroo
DoorDash
Wolt

Work Type

Full-time

Experience Level

3+ years of industry experience

Education Level

BSc, MSc, or PhD in Computer Science or equivalent

About the Company

Deliveroo's GenAI Platform team sits within Machine Learning Platform and builds shared infrastructure for GenAI-powered products.
The team's mission is to increase the velocity of business impact from GenAI.
They run frontier open-weight LLMs and VLMs, optimizing GPU serving, batch inference, and fine-tuning for cost and latency.
The team owns core platform surfaces including LLM Gateway, Agent Gateway, evals infrastructure, guardrails, and cost attribution.

Equal Opportunity

Deliveroo is committed to fostering an environment where everyone can do their best work and feel they belong.
Equality of opportunity is believed in, and candidates from all backgrounds are welcomed regardless of age, gender, ethnicity, disability, sexual orientation, gender identity, socio-economic background, religion, or belief.
Support is offered for individuals with disabilities or long-term health conditions needing assistance with the application process or requiring reasonable adjustments.