Python /AI developer

We are looking for a Python / AI Developer to join a team responsible for the operation and continuous evolution of an enterprise AI platform within a regulated banking environment.

The platform provides secure and governed access to Large Language Models, knowledge bases, enterprise search, conversational agents, RAG services, evaluation frameworks and administration tools.

This is a hands-on role combining software engineering, AI platform engineering, production support, security and technical governance.

Your responsibilities

• Maintain and enhance the AI platform, including Python/FastAPI services, agent engines, connectors, policy controls, databases, background processes and React administration interfaces.
• Operate and improve enterprise search and RAG integrations with SharePoint, intranet and other authorised data sources.
• Develop and maintain AI evaluation frameworks covering quality, groundedness, safety, regression, latency, token usage and cost.
• Implement safeguards against prompt injection, data leakage, unsafe tool execution and inappropriate handling of confidential or personal information.
• Investigate production incidents and improve reliability, performance, scalability, observability and cost efficiency.
• Maintain secure authentication and access controls using OIDC/OAuth2, JWT, RBAC, tenant isolation and resource policies.
• Manage PostgreSQL data models, migrations, transactions and data integrity.
• Support Docker/Kubernetes deployments, Helm, Terraform, CI/CD and cloud infrastructure.
• Implement monitoring, structured logging, metrics, tracing and alerting.
• Develop automated tests covering APIs, databases, security, integrations and user interfaces.
• Produce technical documentation, architecture diagrams, runbooks and operating procedures.
• Participate in code, architecture, security and release-readiness reviews.
• Contribute to knowledge sharing and coaching of internal teams.

Your profile

• 5+ years of relevant experience in software engineering, platform engineering or a related technical role.
• Strong hands-on experience with Python, asynchronous programming, FastAPI, Pydantic and typed application design.
• Strong knowledge of PostgreSQL, SQL, database design, migrations, transactions, concurrency and data integrity.
• Practical experience with LLMs, AI agents, RAG, embeddings, enterprise search, prompt engineering and tool calling.
• Experience designing and implementing automated AI evaluation frameworks.
• Good understanding of AI security risks, including prompt injection, retrieved-content attacks, data leakage and unsafe tool execution.
• Strong knowledge of API security, OIDC/OAuth2, JWT, access control, secrets management and secure development practices.
• Experience with Docker, Kubernetes, Helm, Terraform, CI/CD and Azure or a comparable enterprise cloud platform.
• Experience with observability tools such as OpenTelemetry, Splunk or Prometheus.
• Strong automated-testing capabilities.
• Working knowledge of TypeScript and React.
• Professional proficiency in English.

Nice to have

• Experience with Azure OpenAI, Azure AI Search, Microsoft Graph or SharePoint.
• Knowledge of AI model and agent lifecycle governance.
• Experience in banking, financial services, EU institutions or another regulated environment.
• Knowledge of GDPR, the EU AI Act, DORA or similar regulatory frameworks.
• Experience with performance testing, capacity planning, disaster recovery and service continuity.
• Knowledge of Model Context Protocol (MCP) or similar tool-integration standards.
• Experience with Temporal or other workflow orchestration technologies.
• Experience with multilingual enterprise applications.
• French language skills.

What you will bring You are comfortable working independently and taking ownership of complex technical topics. You combine strong technical judgement with structured troubleshooting and clear communication.

You value secure, maintainable and supportable solutions and are able to explain complex AI concepts to both technical and non-technical stakeholders.

You will contribute to

• Secure and reliable operation of the AI platform.
• Timely resolution of incidents, vulnerabilities and operational risks.
• Controlled delivery of tested and documented platform improvements.
• Continuous improvement of AI evaluation benchmarks and release-readiness processes.
• Up-to-date architecture documentation, runbooks, data models and support procedures.
• Monitoring and reporting of reliability, security, AI quality, usage, cost and technical debt.
• Effective knowledge transfer to enable internal teams to operate and evolve the platform sustainably.