AI Engineer

Description

The team builds AI agents and services that carry out business tasks in enterprise workflows, and the work needs to be dependable in production.

The role covers building, testing and connecting these systems so they run well inside client environments.

Responsibilities

• Build, test and connect production-grade AI agents and services that complete business tasks reliably within enterprise workflows.
• Write agents, prompts, tools, retrieval pipelines and orchestration logic.
• Connect AI components to enterprise APIs, applications, databases and workflow services.
• Write automated tests and evaluation datasets covering functional and non-functional behavior.
• Find the cause of failures in models, retrieval, tool use and integrations.
• Help with secure coding, documentation, peer review and releases.
• Take an active part in agile ceremonies, demos and backlog refinement.

Requirements

• At least 3 years in software, data or AI engineering.
• Strong Python or a comparable language, API development and version control.
• Hands-on work with LLM applications, RAG, agents, embeddings and structured outputs.
• Ability to iterate with product, architecture, data and user-experience colleagues.
• Hands-on experience building agents with at least one production-oriented framework, such as LangChain and LangGraph, Microsoft Agent Framework, Semantic Kernel, OpenAI Agents SDK, AutoGen, CrewAI or an equivalent.
• Solid Python, practical use of FastAPI or a similar API framework, Pydantic or comparable schema validation, asynchronous programming, Git and automated testing.
• Practical experience with tool calling, structured outputs, agent state and memory, hand-offs, guardrails, retries, human-in-the-loop steps and deterministic workflow nodes.
• Experience building RAG pipelines with embeddings, vector or hybrid search, metadata filters, reranking and evaluation datasets.
• Familiarity with MCP, enterprise API integration, queues or events, Docker containers and deployment to Kubernetes or managed application platforms.
• Ability to trace and evaluate agent runs with tools such as LangSmith, MLflow, Langfuse, OpenTelemetry or platform-native equivalents.

Conditions

Hybrid role based in BS1 (LI-BS1 LI-Hybrid).

The company is an equal-opportunity employer.