AI Software Engineer (F/H/NB)
Job description
Design and deploy complete AI agents and agentic systems that execute end-to-end business processes, combining software lifecycle expertise with functional understanding of business needs.
At a glance
- Employment
- Full-time · Employee (employment agreement)
- Work mode
- Hybrid · Bordeaux, France
- Languages
- French – fluent
What you'll do
- Analyze business needs and processes to define automation use cases and task split between agent autonomy and human validation
- Design and develop complete agentic systems, choosing between custom development and low-code/no-code configuration
- Build agent tools: function calling, API and information system integration, MCP servers, asynchronous long-running workflows
- Ensure reliability: error handling and retries, control loops, budget and step limits, behavior facing the unexpected
- Evaluate agents: scenario sets, trajectory analysis, task success rates, LLM-as-judge, non-regression tests
- Observe in production: detailed traces, cost per task, drift and loop detection, dashboards
- Secure autonomy: least-privilege tool permissions, prompt injection protection, isolation of sensitive actions, human validation, compliance
- Integrate into the full SDLC and deploy on the cloud with CI/CD and cost management
- Share: document patterns, train client teams, contribute to SFEIR publications and events
What we're looking for
- 5 years of software development experience (excluding internships and apprenticeships) with cross-functional SDLC vision and solid LLM/AI project experience
- Demonstrated practice creating AI agents: custom development or via low-code/no-code environments
- Knowledge of MCP and inter-agent interoperability protocols (A2A)
- Fine understanding of agent failure modes: drift, loops, wrong tool choice, context loss
- Strong command of APIs, asynchronous and event-driven architectures
- Engineering rigor: tests, observability, reviewed code
- Interpersonal ease and good functional level to exchange with business teams and explain AI agent possibilities and limits
Nice to have
- Experience with agent evaluation and observability (OpenTelemetry, Langfuse...)
- Knowledge of the BMAD methodology
- Google Cloud (Vertex AI, Cloud Run, Gemini)
- Security sensibility: agent threat models, identity and permission management
- RAG notions, seen as an agent tool
- Open source contributions, agentic side projects, talks
Your team
SFEIR Bordeaux
Agency of about fifteen senior engineers and architects, with the proximity and agility of a human-sized structure backed by a large group.
Benefits
Attractive fixed salary, vacation bonus, profit-sharing agreement, sustainable mobility package, health insurance and meal vouchers
- 2 to 3 days of remote work per week
- High-end laptop of choice (MacBook Pro or latest-generation Dell Precision)
How to get hired
- 1HR exchange: alignment on your background, expectations and SFEIR opportunities
- 2Technical session ("PlayOffs"): practical pair-programming evaluation (Algo and GenAI) with two Sfeirians
- 3Business & projection exchange: in-depth discussion on use cases, target missions and client context in Bordeaux
- 4Final interview: strategic exchange with the Agency Director
Apply
About SFEIR
Technology expertise firm specialized in the design, architecture and industrialization of custom digital solutions
Convinced that digital sovereignty is a major strategic issue, SFEIR designs secure, performant and independent architectures, driven by solid partnerships with key players such as SENS and Scaleway.
Mission
Support organizations in their most complex transformations by combining Software Craftsmanship rigor with mastery of future technologies
Key facts
- 950 consultants
- 950 consultants passionate about tech and augmented by AI
- 8 agencies in France, Luxembourg and Belgium
- Anthropic Select partner within the Claude Partner Network
- 15 years of partnership with Google Cloud, AWS, Microsoft, Databricks, Confluent...
- Over 5000 people trained per year via SFEIR Institute
Partners & customers
What they value
- A collective where technical culture prevails
- Expert career paths (Individual Contributor) allowing progression in high technical mastery without switching to organizational management
