Advanced AI Engineer

Relativity is a leading legal data intelligence company building AI-powered cloud platform RelativityOne to assist law firms, corporations, and government agencies in organizing data and extracting actionable insights for high-stakes legal matters.

• 3+ years of professional software engineering experience with strong, recent Python development in production systems.
• Experience building LLM-powered or agentic systems using frameworks such as LangChain and LangGraph, including tool calling, orchestration, and state management.
• Good design instincts and ability to write clean, testable code.
• Solid understanding of modern async Python, API and service design, and relational databases (PostgreSQL).
• Experience delivering cloud-native systems using Azure or similar platforms, CI/CD, Docker, and 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 architectures, agent memory, or human-in-the-loop patterns.
• Familiarity with Model Context Protocol (MCP) or agent-to-agent (A2A) interoperability.
• Experience with Retrieval-Augmented Generation (RAG), retrieval systems, citations, and evaluating LLM output quality.
• Knowledge of LLM observability and tracing tools such as MLflow, OpenTelemetry, and evaluation frameworks.
• Experience with Infrastructure-as-Code tools like Pulumi or Terraform.

• Build and extend the agent runtime in Python using LangGraph, LangChain, and Deep Agents including stateful graph agents and multi-agent orchestration.
• Implement harness capabilities such as streaming output, tool calling, human-in-the-loop review, conversation branching, session memory, and checkpoint/resume for long-running tasks.
• Contribute to extensibility and protocol layers including Model Context Protocol (MCP) tool servers, Agent-to-Agent (A2A) interoperability, and runtime configuration registry.
• Facilitate agents' usage of various LLM providers like OpenAI and Gemini.
• Write clean, well-tested code, participate in design and code reviews, and own components through production.
• Collaborate with teammates and application teams to move new capabilities from experiments into production safely.