Senior AI Engineer: Agent Harness (Hybrid/Remote)

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

Benefits offered by this job

Competitive compensation

Equity program

Parental leave

DTO

Job summary

Relativity is seeking an Advanced AI Engineer to join the Agent Harness team. You will build and extend Relativity’s agent runtime, working hands-on with LangGraph, LangChain, and Deep Agents to tailor runtimes for Relativity’s needs and scale agent orchestration.

You will mature the harness with capabilities like long-session handling and broader protocol support, collaborating with Applied Science and aiR application teams to move designs into production safely in a fast-moving space.

Qualifications

• 3+ years of professional software engineering experience building production systems.
• Experience building LLM-powered or agentic systems with LangChain/LangGraph or equivalent.
• Strong design instincts: clean, testable code and component design.
• Solid understanding of modern async Python, API design, and relational data (PostgreSQL).

Responsibilities

• Build and extend the agent runtime in Python using LangGraph, LangChain, and Deep Agents.
• Implement harness capabilities: streaming, tool calling, memory, and long-running sessions.
• Design and extend protocol layers: MCP, A2A interoperability, and runtime config registry.
• Work with multiple LLM providers (OpenAI, Gemini).
• Write clean, well-tested code and participate in reviews; own components to production.
• Collaborate with Applied Science and aiR teams to move capabilities from experiment to production.

Skills

Python

Async programming

API design

PostgreSQL

Cloud CI/CD

Education

Bachelor's degree in CS or related

Tools

LangChain

LangGraph

DeepAgents

Docker

Kubernetes

Azure

Job description

Relativity is seeking an Advanced AI Engineer to join the Agent Harness team. You will build and extend Relativity’s agent runtime, working hands-on with LangGraph, LangChain, and Deep Agents to tailor runtimes for Relativity’s needs and scale agent orchestration.

You will mature the harness with capabilities like long-session handling and broader protocol support, collaborating with Applied Science and aiR application teams to move designs into production safely in a fast-moving space.