AI Engineer

We are looking for an AI Engineer to join a team building production-grade AI solutions for complex business processes.

In this role, you will work at the intersection of software engineering, LLMs and agentic systems. You will design AI agents that can use tools, interact with enterprise systems, coordinate multi-step tasks and work together as part of larger AI workflows.

This is a hands-on engineering role, with a strong focus on Python development and production-ready AI architectures.

What you will do

• Design and develop AI agents capable of handling multi-step tasks and business workflows.

• Build reliable agent architectures combining LLM-based reasoning with conventional Python services.

• Develop APIs and integrations connecting AI solutions with enterprise applications.

• Create tools that agents can discover and use, including solutions based on Model Context Protocol (MCP).

• Build workflow orchestration using graph-based approaches, including state management and human approval steps where required.

• Develop mechanisms for communication and cooperation between multiple AI agents.

• Improve the reliability, response time and cost efficiency of AI-powered applications.

• Work closely with software engineers, architects and business stakeholders to turn business requirements into scalable AI solutions.

• Contribute to the design of production architectures, testing strategies and operational practices for AI applications.

What we are looking for

• Strong experience in software engineering with hands-on experience delivering LLM or agent-based applications.

• Advanced Python skills and practical experience with:

  • asyncio

  • FastAPI or a comparable framework

  • Pydantic

  • pytest / pytest-asyncio

• Solid understanding of modern LLM application development, particularly:

  • tool/function calling

  • structured outputs

  • agent orchestration

  • multi-agent architectures

  • workflow automation

  • latency and cost optimization

• Commercial experience with at least one agent/LLM framework such as LangChain, LangGraph, CrewAI, OpenAI Agents SDK, Claude Agent SDK or a comparable technology.

• Practical knowledge of MCP and experience developing or integrating agent tools.

• Experience with workflow orchestration and stateful AI processes.

• Experience integrating applications through REST APIs.

• Good understanding of modern authentication and authorization, such as OAuth2, SSO or Microsoft Entra ID/Azure AD.

• Experience with Redis or a comparable distributed data/cache solution.

• Familiarity with Docker and containerized applications.

Nice to have

• Experience with Langfuse, OpenTelemetry, Datadog or other observability platforms.

• Exposure to cloud-based storage, search and AI services.

• Experience evaluating LLM applications and measuring AI output quality.

• Knowledge of specification-driven development.

• Experience working on solutions for highly regulated or enterprise environments.

• Previous experience delivering AI products within large organizations.

Technology stack

Python · LLMs · Agentic AI · MCP · LangGraph · LangChain · FastAPI · Pydantic · asyncio · pytest · Redis · REST APIs · OAuth2 · Microsoft Entra ID · Docker · OpenTelemetry

The project

You will be working on enterprise AI solutions designed to automate and support complex business workflows. The systems combine LLM-based agents with traditional software components, APIs and enterprise applications.

The focus is on building robust, maintainable solutions that can move beyond simple chatbots and actually plan, execute and coordinate real-world tasks.

If you enjoy solving engineering problems around LLMs, AI agents, orchestration and scalable Python systems, this role will give you the opportunity to work on that technology in a production environment.