SlipstreamJobs tracks this role from the company's public career site. Apply directly on the employer's site.
Motorway is the UK's largest online car-selling platform, connecting private sellers with over 8,000 dealers nationwide. The company has raised £143 million in Series C funding and is backed by leading technology investors.
The GenAI Engineering team sits within Motorway's Data and AI function, owning AI features that shape how buyers and sellers experience the marketplace—from agentic workflows in customer journeys to LLM-powered tooling for dealers. The team has a track record of successful deployments with a short feedback loop: features typically reach production within weeks.
As a Senior GenAI Engineer, you will own AI features end-to-end, from ambiguous problem definition through to reliable, observable production systems. You'll build retrieval and data foundations, treating retrieval quality as a first-class engineering problem. You'll design evaluation and monitoring approaches that make quality, reliability, and safety measurable. You'll build AI applications and agents using LLMs, orchestration, APIs, and data systems while applying solid production software practices.
You'll make critical decisions on models, cost, and latency that shape feature economics. You'll prototype quickly, identify reusable patterns, and harden them into components the team adopts. You'll raise quality through code review and design feedback, and represent technical decisions directly to product managers, translating model behavior into business consequences.
You should have shipped AI or ML systems that real users depend on and stayed close to production to understand failure modes. You need strong Python and SQL (used extensively for data work: assembling grounding data, building golden datasets, debugging failures). You've invested deliberately in software engineering craft: testing, error handling, CI/CD, observability, and MLOps practices. You're hands-on across the GenAI stack: LLM APIs, retrieval and vector stores, agents with tool use, structured outputs, and cloud infrastructure (AWS and GCP). You have a real point of view on evaluation, understand how models fail (hallucination, prompt injection), and know when to reach for a model versus simpler solutions.
