Advanced AI Engineer
KcuraPosting Type
Hybrid/Remote Poland
Job Overview
WHO WE ARERelativity is a leading legal data intelligence company building technology that helps users organize data, discover the truth, and act on it with confidence. Our AI-powered, cloud platform, RelativityOne, transforms massive volumes of complex information into actionable insights for litigation, investigations, regulatory inquiries, and other high-stakes legal work where accuracy and trust are crucial.
The world’s largest law firms, corporations, and government agencies rely on Relativity’s legal AI software to securely surface and manage the most relevant information in their matters.
WHAT WE DO
At Relativity, engineers do more than write code — they build systems that let users uncover insights from complex data at scale using cloud-native architecture, AI, and modern tools.
The AI Platform group builds the agentic foundation that powers Relativity’s AI products, including aiR Assist and ClaiR. The Agent Harness team owns the runtime that runs our agents: agent orchestration, tool and skill execution, memory, and the protocols that let agents interact with each other and with external systems.
ABOUT THE ROLE
As an Advanced AI Engineer on the Agent Harness team, you will build and extend Relativity’s agent runtime — working hands-on with industry frameworks like LangGraph, LangChain, and Deep Agents and fitting them to Relativity’s needs so every Relativity agent has a solid runtime to build on.
You will help mature the harness with industry-standard capabilities like long-session handling or broader protocol support, so it is ready before ClaiR and aiR Assist multiply agentic traffic, rather than after.
You will contribute to design discussions and turn agreed designs into well-tested, production-ready capabilities that application teams adopt.
You will work in a fast-moving space where agent architecture changes quickly, and grow your depth in agent engineering as you go.
Job Description and Requirements
WHAT YOU’LL DO
Build and extend the agent runtime in Python using LangGraph, LangChain, and Deep Agents (deepagents) — stateful graph agents, harness profiles, and multi-agent / subagent orchestration.
Implement harness capabilities that application teams rely on — for example streaming and structured/generative output, tool calling, human-in-the-loop review, conversation branching and message queues, session memory, and checkpoint/resume (time-travel) over long-running work.
Contribute to the harness’s extensibility and protocol layer: Model Context Protocol (MCP) tool servers and clients, Agent-to-Agent (A2A) interoperability, and a registry of skills, tools, and configurations composed at runtime.
Help agents use the model that fits each use case, working across a range of LLM providers (e.g. OpenAI, Gemini).
Write clean, well-tested code and participate in design and code reviews; take ownership of components and see them through to production.
Collaborate with teammates, Applied Science, and aiR application teams to move new capabilities from experiment into production safely.
WHAT WE’RE LOOKING FOR
Required
3+ years of professional software engineering experience, with strong, recent Python building production systems.
Experience building LLM-powered or agentic systems with frameworks such as LangChain / LangGraph (or equivalent), including tool calling, orchestration, and agent state management.
Good design instincts — writing clean, testable code and contributing to the design of the components you own.
Solid understanding of modern async Python, API and service design, and relational data (PostgreSQL).
Experience delivering cloud-native systems (Azure or similar) with CI/CD and containers (Docker); familiarity with Kubernetes.
Bachelor’s degree in Computer Science, Engineering, or equivalent experience; English proficiency for technical communication.
Preferred
Experience with Deep Agents, multi-agent / subagent architectures, agent memory, or human-in-the-loop patterns.
Familiarity with the Model Context Protocol (MCP) or agent-to-agent (A2A) interoperability.
Experience with RAG and retrieval systems, citations, and evaluating LLM output quality.
Familiarity with LLM observability and tracing (MLflow, OpenTelemetry) and evals for safe model upgrades — nice to have.
Infrastructure-as-code (Pulumi/Terraform).
WHY WE COULD BE A GREAT FIT
Impactful Mission
Build systems that help customers organize data, discover the truth, and act on it in high-stakes legal matters.
Engineering at Scale
Work on distributed, cloud-native systems that process large volumes of data.
Cutting-Edge Technology
Build with AI, cloud platforms, and scalable architectures shaping legal tech.
Growth and Ownership
Gain experience owning systems end-to-end across cloud and distributed environments.
Collaborative Culture
Work in a team focused on knowledge sharing and continuous improvement.
Inclusive Environment
Diverse perspectives create stronger teams and better outcomes.
Compensation and Benefits
Competitive salary, benefits, DTO, parental leave, and equity program.
Relativity is committed to competitive, fair, and equitable compensation practices.
This position is eligible for total compensation which includes a competitive base salary, an annual performance bonus, and long-term incentives.
The expected salary range for this role is between following values:
188 000 and 282 000PLNThe final offered salary will be based on several factors, including but not limited to the candidate's depth of experience, skill set, qualifications, and internal pay equity. Hiring at the top end of the range would not be typical, to allow for future meaningful salary growth in this position.
Required Skills:
Algorithms, Artificial Neural Networks (ANNS), Big Data, Computer Vision, Data Science, Deep Learning, Machine Learning (ML), Natural Language, Natural Language Processing (NLP), Software Engineering