AI Product Engineer

Magentic · Londonsenior

In short

▸Construyes el núcleo agente de un producto de IA para automatizar flujos de compras empresariales.
▸Trabajas end-to-end: desde marcos de agentes hasta integración con ERP de clientes.
▸El desafío: sistemas agentes robustos que evitan errores caros en un mercado de $3tn.

Proficiency in English is required for collaboration across global teams.

In ~1 minute you get: who interviews you, the likely questions answered from your CV, and your CV tailored to this job. Free, no card.

🎧Land the interview? Bring the copilot. Our free extension listens to the live interview and flashes 3-4-word anchors from your resume and prep — glance, connect, talk. Get the extension →

What they ask for

✓Experiencia en desarrollo y despliegue de soluciones con LLM en producción.
✓Conocimiento profundo de modelos de lenguaje y fundamentos de ciencias de la computación.
✓Habilidades para construir features desde cero en Python.
✓Capacidad para colaborar con stakeholders técnicos y no técnicos.
✓Experiencia con frameworks de agentes o workflows multi-agente.
✓Experiencia en benchmarking de LLMs en rendimiento, seguridad y comportamiento.

Don't tick every box? That's normal — your free dossier shows your gaps and how to cover them in the interview.

LLMPythonAgentic workflowsMulti-agent collaborationERP integrationBenchmarkingPerformance monitoringSafety monitoringBehavioural monitoringProduction deployment

Who should you write to at Magentic?

Your free dossier identifies the people who'd interview you — their background, what they value, and how to reach out so you stand out before applying.

The Role We're looking for an AI Engineer to build the agentic core of our product. You'll work closely with our CTO and own LLM-based features and agentic workflows end to end, from the agent framework through to the tooling that connects it to a customer's ERP. You’ll ship the cutting edge models and paradigms to Fortune 500 procurement teams. Procurement is a demanding domain for agents: long-running workflows over messy data, where a wrong answer costs a customer real money. You'll decide how multi-agent collaboration works here, and how we benchmark it for performance, safety and behaviour. We're building next-generation agentic systems that can manage entire procurement workflows, with a mission to make global manufacturing supply chains more resilient to an ever-changing world. That's a $3tn market opportunity. We're backed by world-class investors including Sequoia Capital, and you'll be joining a team bringing together experience from OpenAI, Meta, Revolut, NASA and McKinsey. What You’ll Do Own development and deployment of LLM-based features and agentic workflows end-to-end Develop new agentic frameworks to handle multi-agent collaboration. Benchmark LLMs across performance, safety and behavioural monitoring. Operationalise AI features by building tools to connect them to customer systems Collaborate with customers and internal teams to understand customer problems and design optimal solutions You Might Be a Great Fit if You Have engineering experience at tech and product-driven companies, so you know what great code looks like Have experience shipping LLM-based solutions to production Have a deep understanding of the core technology behind language models, as well as computer science fundamentals Have built features end-to-end in Python Enjoy communicating with both technical and non-technical stakeholders. Benefits At Magentic, we recognise and reward the talent that drives our success. We offer: Competitive Equity : play a real part in Magentic’s upside A salary of £90,000 - £110,000 per annum Enhanced parental leave 25 days holiday exc bank holidays, plus an extra day for our Christmas shutdown In-office lunches provided Salary sacrifice pension and nursery schemes Hybrid London HQ (3 days per week, with flex if you have appointments etc) Annual team retreat —a fully-funded off-site to recharge, bond, and build Our Interview Process We can move quickly through these stages, so let us know if you have any timelines we need to meet. Initial call (30 mins) : this first step is an opportunity for you to hear more about Magentic and the role, and for us to learn more about how your experience aligns with the role. Skills interview (45 mins): in this step, we'll ask you to prepare a presentation and take Q&A. In-person interview (half-day, paid): for the final step, we invite you to come meet the team in-person. We find this is the best way for candidates to get a sense of what working at Magentic is like. This day will include a culture interview, founder interview and a presentation task / discussion with the team. Equal Opportunities and Accommodations Statement At Magentic, our mission is to build AI that helps solve some of the world's most complex real world problems. We believe building a diverse workforce will be the key to solving this for our customers. Magentic is committed to creating a truly inclusive team and we’re proud to be an equal-opportunity employer. As we grow, we're intentional about building teams with a broad range of backgrounds, experiences and viewpoints, recognising that this leads to better ideas, stronger collaboration and better outcomes for our customers therefore we strongly encourage applications from all backgrounds and cultures to apply. We recognise that some groups remain underrepresented within the industry and are committed to creating an environment that celebrates and supports everyone.

Don't apply unprepared

We research who's interviewing you, tailor your CV and rehearse you live — first one free.