2 months ago
Madrid, SpainMid Level
Responsibilities
- Build reusable AI platform components, including retrieval and context engines, guardrail and evaluation libraries, MCP/tool layers, scaffolder templates, SDKs, and stable APIs.
- Develop grounded assistants, copilots, and wizards for BASF’s product lifecycle across the portal, IDE, and Teams.
- Expose read-first, RBAC- and tenant-aware capabilities through MCP, SDK, and API interfaces for humans and agents.
- Create evaluation harnesses, golden tests, and retrieval-quality metrics for correctness, grounding, and regression testing.
- Improve prompt and version management, model adaptation, CI/CD, and the path from AI experimentation to production.
- Operate multi-tenant services with observability, distributed tracing, per-product cost attribution, security, auditability, and governance.
- Apply appropriate deterministic, structured-output, human-in-the-loop, and agentic patterns while gating state-changing actions.
Requirements
- BSc or MSc in Computer Science, Software Engineering, AI, or a related field.
- At least 4 years of software engineering or platform development experience with recent generative AI and/or agentic-systems experience.
- Strong Python skills and hands-on experience building LLM-powered applications using RAG and agentic patterns.
- Experience designing evaluation harnesses, golden tests, and retrieval-quality metrics for LLM/RAG systems.
- Experience building production backend services and versioned APIs, preferably with FastAPI, Pydantic, and asynchronous programming.
- Experience building reusable self-service platform components, developer-experience tooling, paved roads, templates, SDKs, and golden paths.
- Hands-on Azure and containerization experience with Docker and Kubernetes/AKS, plus infrastructure-as-code using HCL/Terraform.
- Experience with relational or non-relational databases, PostgreSQL, vector stores, CI/CD, Git, GitHub Actions, and production observability.
- Familiarity with OpenAI, Anthropic, Mistral, Azure AI Foundry, Databricks, MCP, authentication, authorization, RBAC, tenant isolation, and the OWASP LLM Top 10.
- Nice-to-have experience includes Databricks Unity Catalog, TypeScript, Grafana, MLflow, data pipelines, FinOps, RabbitMQ, Azure Event Grid, workflow engines, OpenTelemetry, distributed tracing, and EnvoyProxy.
Benefits
- Secure work environment prioritizing health, safety, and wellbeing.
- Flexible work schedule and home-office options.
- Learning and development opportunities.
- 25 holiday days per year plus 5 additional readjustment days.
- Collaborative, trustful, and innovative work environment.
- International team and global project participation.
- Relocation assistance to Madrid.
- The role supports BASF quality, environmental, health, safety, and energy standards and continuous-improvement initiatives.
Tech Stack
AzureDatabricksDockerFastAPIGitGitHub ActionsGrafanaKubernetesMLflowPostgreSQLPythonRabbitMQTerraformTypeScript
Categories
About BASF SE
BASF SE is a public chemical manufacturer that produces basic chemicals, advanced materials, surface technologies, and agricultural solutions for customers in industries such as automotive, construction, and consumer goods, as well as farmers. It sells globally through a portfolio of business segments and R&D-driven product lines. Founded in 1865 and headquartered in Ludwigshafen, Germany, BASF is listed on the Frankfurt Stock Exchange.