Senior AI Engineer — Agent Harness & LLM Orchestration

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

Benefits offered by this job

Equity program

Parental leave

DTO (time off)

Job summary

Relativity is seeking an Advanced AI Engineer on the Agent Harness team to build and extend Relativity’s agent runtime, using LangGraph, LangChain, and Deep Agents to empower scalable AI-powered legal data solutions.

You will collaborate across Applied Science and aiR teams, ensure production-grade, testable code, and contribute to design discussions while advancing long-session handling and multi-agent orchestration in a fast-moving space.

Qualifications

• 3+ years of professional software engineering experience building production systems in Python.
• Experience building LLM-powered or agentic systems with LangChain/LangGraph, including tool calling and orchestration.
• Strong design sense, clean, testable code and ownership of components.
• Solid understanding of async Python, API/service design, and PostgreSQL.
• Experience delivering cloud-native systems with CI/CD and containers; familiar with Kubernetes.
• Bachelor’s degree in CS/Engineering or equivalent; English for technical communication.

Responsibilities

• Build and extend the agent runtime in Python using LangGraph, LangChain, and Deep Agents.
• Implement harness capabilities like streaming output, tool calling, and session memory.
• Contribute to extensibility, MCP tool servers, A2A interoperability, and runtime configurations.
• Work across LLM providers (OpenAI, Gemini) to select appropriate models.
• Write clean, tested code and participate in design and code reviews for production readiness.
• Collaborate with Applied Science and aiR teams to move capabilities from experiment to production.

Skills

Python

LangChain

LangGraph

Async Python

PostgreSQL

Education

Bachelor’s degree in Computer Science or related field

Tools

Docker

Kubernetes

Azure

CI/CD

Job description

Relativity is seeking an Advanced AI Engineer on the Agent Harness team to build and extend Relativity’s agent runtime, using LangGraph, LangChain, and Deep Agents to empower scalable AI-powered legal data solutions.

You will collaborate across Applied Science and aiR teams, ensure production-grade, testable code, and contribute to design discussions while advancing long-session handling and multi-agent orchestration in a fast-moving space.