Advanced AI Engineer
Posted 23hrs ago
Employment Information
Report this job
Job expired or something wrong with this job?
Job Description
Advanced AI Engineer building Relativity’s Python agent runtime for legal data intelligence. Extending LangGraph-based orchestration, memory, protocols, and production AI capabilities.
Responsibilities:
- Build and extend Relativity’s agent runtime in Python using LangGraph, LangChain, and Deep Agents
- Implement stateful graph agents, harness profiles, and multi-agent/subagent orchestration
- Develop streaming and structured/generative output, tool calling, human-in-the-loop review, conversation branching, message queues, session memory, and checkpoint/resume capabilities
- Contribute to the harness extensibility and protocol layer, including MCP tool servers and clients, A2A interoperability, and runtime registries
- Enable agents to use appropriate models across LLM providers such as OpenAI and Gemini
- Write clean, well-tested, production-ready code
- Participate in design and code reviews
- Own components through production delivery
- Collaborate with teammates, Applied Science, and aiR application teams to move capabilities from experimentation into production safely
Requirements:
- 3+ years of professional software engineering experience with strong, recent Python experience building production systems
- Experience building LLM-powered or agentic systems with LangChain, LangGraph, or equivalent frameworks, including tool calling, orchestration, and agent state management
- Good design instincts, including clean, testable code and component design
- Solid understanding of modern async Python, API and service design, and relational data, especially PostgreSQL
- Experience delivering cloud-native systems with Azure or similar, CI/CD, and 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
- Preferred: familiarity with Model Context Protocol (MCP) or agent-to-agent (A2A) interoperability
- Preferred: experience with RAG and retrieval systems, citations, and evaluating LLM output quality
- Preferred: familiarity with LLM observability and tracing, including MLflow and OpenTelemetry, and evals for safe model upgrades
- Preferred: infrastructure-as-code experience with Pulumi or Terraform
Benefits:
- Competitive salary
- Benefits
- DTO
- Parental leave
- Equity program
- Annual performance bonus
- Long-term incentives
- Growth and ownership opportunities
- Knowledge sharing and continuous improvement
- Inclusive, diverse work environment















