Design and implement AI agents and multi-agent systems for real-world business use cases.
Build and maintain agentic workflows, including orchestration, tool usage, and inter-agent communication.
Develop integrations between agents and enterprise systems (APIs, databases, SaaS platforms).
Work with semantic layers and contextual data models to improve agent reasoning and performance.
Implement and manage MCP-like architectures, ensuring proper context sharing and tool connectivity.
Collaborate with data and platform teams to leverage Databricks and modern data stacks.
Ensure solutions are production-ready, scalable, and aligned with governance and security requirements.
Translate business problems into agent-based AI solutions with clear technical execution paths.
Stay up to date with the latest advancements in agentic AI frameworks and LLM ecosystems.

Proven experience building AI agents or agent-based systems.
Solid understanding of multi-agent architectures, tool usage / “skills” in agents, agent orchestration patterns
Experience with Model Context Protocol (MCP) or similar approaches to context/tool integration.
Hands-on experience coding agent solutions (not only using no-code tools).
Strong programming skills in Python.
Solid understanding of APIs and integrations, authentication flows, distributed systems.
Familiarity with LLM frameworks (LangChain, LangGraph, or similar).
Experience working with semantic layers / knowledge representation is a strong plus.

AI Engineer

Key skills