Staff AI Engineer in Core Engineering

This is a hands-on, deeply technical role. Most of your time goes into writing and reviewing code, designing systems, and debugging behaviour that is probabilistic rather than deterministic. The scope is enterprise-wide: what you build is consumed by engineering, product, data and business teams across the group, in around 50 countries. Reliability, architecture, quality, observability, security and cost are therefore requirements from day one, not a later hardening phase.

As a Staff engineer, your impact is measured less by what you ship alone than by what you make possible for others: the frameworks, standards and habits that let dozens of engineers build agentic features quickly and safely. You earn that influence through credibility, clear writing and teaching, not through hierarchy.

Stack: Python, Java, GCP (incl. Vertex AI), Kubernetes, Kafka & Kafka Connect, MySQL, MongoDB, Snowflake, Spark, KrakenD, n8n.

Key Responsibilities

• Build our enterprise agentic framework: orchestration, retrieval and collaboration between multiple agents: tool and MCP integration, planning and hand-off, shared state, human-in-the-loop checkpoints, and graceful failure.
• Write production-grade code: well-structured, efficient and testable, across production services, experimentation harnesses, and internal tooling that makes agentic capabilities easy for other functions to adopt.
• Make AI systems measurable and trustworthy: golden datasets, offline and online evals, regression suites in CI, guardrails, tracing across multi-step agent runs, and telemetry on latency, quality, token spend and failure modes.
• Set standards and design for security: work with platform, architecture and security on system design, internal protocols and API standards, and bring structural decisions to the Engineering Committee.
• Raise the level around you: code reviews, technical discussions, design docs and workshops, mentoring, and contributing to a culture of engineering excellence.
• Champion a cross-cutting technical vision and standards: help define code and architecture guidelines, guide several teams towards iterative development and autonomous decision-making, weighing the value of complex patterns against their implementation cost.

What success looks like in your first year

• Squads outside Agentic & Automation ship agentic features on a framework without needing you in the room.
• Every production AI capability has an eval suite, a cost profile and a visible dashboard.
• The organisation has documented, adopted standards for agent design, tool exposure and retrieval, and reuses them by default., * Ambassador program: an employee volunteering initiative dedicated to all Believers interested in having a positive impact on Diversity, Equity & Inclusion (DEI), wellbeing and the planet.
• Implementation of the sustainable mobility package “Forfait mobilité durable” => Reimbursement of up to 600€ for public transport/low carbon footprint
• 5 calendar days 2nd parent leave with 100% pay (in addition to the legal paternity or adoption leave)

• 5+ years in software engineering, including a meaningful stretch at a cross-team level of influence (Staff, Principal or equivalent), and recent experience taking LLM-based systems into production, not only prototypes.
• Strong fundamentals: depth in coding, plus API design, concurrency, data modelling, testing, CI/CD and containerised deployment.
• Agentic systems in practice: orchestration and tool calling, structured outputs, multi-step planning, memory and state, and the operational reality of long-running, partially-failing workflows.
• AI workflows: access-controlled retrieval, LLM-as-judge and its limits, drift detection, model routing, caching, compression, observability and tracing for non-deterministic systems.
• Influence without authority: aligning multiple stakeholders, writing documents that unblock decisions, mentoring, connecting technical choices to product value, and creating an environment where respectful disagreement improves the outcome. Clear communication in English (our working language).
• Craft culture & engineering excellence: deep, demonstrated craft sensibility; the ability not only to apply good practices but to teach them, defend them and embed them culturally; strong command of testing, software quality and observability, and comfort with data-driven steering (DORA, NFRs).

• Remote working policy
• A wellness program “Pauses” with many activities and animations in-house
• Access to Eutelmed, a digital mental health and well-being platform that allows you to speak with an experienced psychologist
• A healthy and eco-responsible company restaurant
• Individual or family health insurance
• CSE benefits
• A rooftop
• A gym with free classes

At all stages of their careers, Believers are an important part of what we are doing: shaping the future of the music industry.

We need teams that truly reflect the diversity of our clients: our international presence is an inspiring and enriching work environment for each one of us, with daily opportunities to connect with our colleagues all over the world.

We have two hearts at Believe - our People and our Artists.

We believe in THE POWER OF OUR PEOPLE, who grow every day to develop their potential… We aim to provide our Believers with the best environment to thrive.