Required skills
- AI Engineering
- Machine Learning Engineering
- Software Engineering
- LLM Applications
- AI Agents
- RAG
- Agent Orchestration
- Tool Calling
- Python
- API Integration
- Automated Testing
- Code Review
- Modular Software Development
- Databricks
- MLflow
- Mosaic AI
- Model Serving
- Vector Search
- Unity Catalog
- Microsoft Azure
- Azure OpenAI
- Managed Identities
- Key Vault
- Storage
- Networking
- LangGraph
- LangChain
- Semantic Kernel
- GitLab CI/CD
- Terraform
Languages: German
Job description
Seeking an AI Engineer to design, develop, and deploy intelligent AI Agents on Databricks and Azure, focusing on LLMOps, Cloud Architecture, and agent-based applications.
Project overview
For our end customer, we are looking for an AI Engineer - AI Agents & Deployment on Databricks and Azure (m/f/d) starting as soon as possible for a long-term engagement.
Requirements
Several years of experience as an AI Engineer, Machine Learning Engineer, Software Engineer, or in a comparable technical role.
Knowledge of the Model Context Protocol (MCP) and patterns for multi-agent or agent-to-agent communication.
- Practical experience with LLM applications and AI Agents, ideally with RAG, Agent Orchestration, Tool Calling, and productive deployment.
- Very good knowledge of Python as well as API integration, automated tests, code reviews, and modular software development.
- Profound experience with Databricks, for example with MLflow, Mosaic AI, Model Serving, Vector Search, and Unity Catalog.
- Good knowledge of the Microsoft Azure platform, especially Azure OpenAI, Managed Identities, Key Vault, Storage, and Networking.
- Experience with agent and LLM frameworks, for example LangGraph, LangChain, or Semantic Kernel, and stateful workflows.
- Practical experience with GitLab CI/CD for testing, versioning, and automated deployment of AI applications.
- Practical experience with Terraform (Infrastructure as Code) for the deployment of Azure and Databricks resources.
- Solid understanding of LLMOps, Agent Evaluation, and Observability, including systematic quality controls.
- Knowledge in AI Security, Data Protection, and Governance, secure model access, Guardrails, and the protection of sensitive information.
- Ability to deploy AI Agents productively, reliably, and scalably, and to translate business requirements into robust solutions.
- Experience with FastAPI, Docker, and Kubernetes for operating containerized agent services and APIs.
- Knowledge of Spark, SQL, Delta Lake, and Databricks Workflows for data preparation and AI-driven processes.
- Experience with Human-in-the-Loop, structured outputs, and controlled rollouts for AI applications.
- Experience in regulated or data-privacy-sensitive corporate environments.
Project details
Cologne / remote (50/50)
The scope of work is the conception, development, and productive deployment of intelligent AI Agents on Databricks and Azure – secure, traceable, and scalable. This includes AI Engineering, LLMOps, and Cloud Architecture, as well as the realization of agent-based applications to connect enterprise data, Large Language Models, and internal systems in collaboration with a cross-functional team.
Description:
Conception, development, and operation of productive AI agent solutions on Databricks and Azure – from the initial prototype to scalable deployment.
- Development of AI agents and multi-agent workflows for the targeted connection of Large Language Models, enterprise data, APIs, and internal systems.
- Implementation of RAG, Tool Calling, and Agent Orchestration, as well as development of reusable tools, prompts, and state and context components.
- Integration of Azure OpenAI and other Foundation Models into Databricks as well as into existing application and data landscapes.
- Development of Python-based agent services and APIs and their integration into existing backend and cloud architectures.
- Use of Databricks Mosaic AI, Model Serving, and MLflow for versioning, evaluation, deployment, and monitoring of models and agents.
- Implementation of Vector Search, Embeddings, and Retrieval Pipelines for controlled access to relevant enterprise data.
- Orchestration of agent, data, and automation processes with Databricks Workflows and defined tool accesses.
- Automation of deployment with GitLab CI/CD and Terraform, including reproducible environments, tests, and traceable releases.
- Development of evaluations, tracing, and monitoring for response quality, groundedness, security, latency, cost, and reliability.
- Establishment of Guardrails, authorization concepts, and Human-in-the-Loop processes for the responsible use of AI Agents.
- Ensuring security and governance with Unity Catalog, Managed Identities, Key Vault, RBAC, Private Endpoints, and Logging.
- Close collaboration with Product Owners, business departments, Data, Backend, and Cloud teams, as well as Security and Privacy on productive agent use cases.
- Documentation of agent logic, tool interfaces, data flows, architecture, evaluation methods, and runbooks for sustainable operation.
- Start: ab sofort
- Remote: hybrid
- Location: Köln, Deutschland, DE
- Languages: German
Indexed by 9am's meta-search. You are a job provider? Claim or manage this listing
Found on FreelancerMap DE