Senior AI Engineer: Agent Runtime & LLM Orchestration

Relativity; Kraków; Hybrid; PLN 188,000 - 282,000; Full time

Job summary

Relativity is seeking an Advanced AI Engineer in Kraków to join the Agent Harness team. You will build and extend Relativity’s agent runtime, collaborating with LangGraph, LangChain, and Deep Agents to tailor solutions for complex legal data workloads.

You’ll contribute to production-grade capabilities, ensure robust long-session handling, and work with Applied Science and aiR teams to move features from experimentation to scalable deployments in a fast-moving AI platform.

Qualifications

• 3+ years of professional software engineering experience
• Experience building LLM-powered or agentic systems with LangChain / LangGraph, including tool calling and orchestration
• Good design instincts and clean, testable code
• Strong async Python, API/service design, and relational data (PostgreSQL)
• Experience delivering cloud-native systems with CI/CD, Docker, and familiarity with Kubernetes
• Bachelor’s degree in Computer Science, Engineering, or equivalent; English proficiency for technical communication

Responsibilities

• Build and extend the agent runtime in Python using LangGraph, LangChain, and Deep Agents
• Implement harness capabilities such as streaming, structured output, tool calling, and memory
• Develop MCP tool servers, A2A interoperability, and runtime configurations
• Work with multiple LLM providers (OpenAI, Gemini) for various use cases
• Write clean, well-tested code and participate in design/code reviews
• Collaborate with Applied Science and aiR teams to move features to production

Skills

Python

LangChain

LangGraph

LLM

PostgreSQL

Docker

Kubernetes

CI/CD

Education

Bachelor's degree in CS/Engineering

Tools

OpenAI

Gemini

Job description

Relativity is seeking an Advanced AI Engineer in Kraków to join the Agent Harness team. You will build and extend Relativity’s agent runtime, collaborating with LangGraph, LangChain, and Deep Agents to tailor solutions for complex legal data workloads.

You’ll contribute to production-grade capabilities, ensure robust long-session handling, and work with Applied Science and aiR teams to move features from experimentation to scalable deployments in a fast-moving AI platform.