Advanced AI Engineer

This is a fully remote position, open to applicants in Poland.

📋 Description

• Develop and enhance Relativity’s agent runtime using Python with LangGraph, LangChain, and Deep Agents.

• Implement stateful graph agents, harness profiles, and orchestrate multi-agent/subagent functionalities.

• Create streaming and structured/generative outputs, enabling tool calling, human-in-the-loop reviews, conversation branching, message queuing, session memory, and checkpoint/resume features.

• Contribute to the extensibility of the harness and the protocol layer, which includes MCP tool servers and clients, A2A interoperability, and runtime registries.

• Equip agents with the ability to utilize suitable models from various LLM providers, such as OpenAI and Gemini.

• Produce clean, thoroughly tested, and production-ready code.

• Engage in design and code review processes.

• Take ownership of components throughout the production delivery cycle.

• Collaborate with colleagues, Applied Science, and aiR application teams to transition capabilities from experimentation to production safely.

⛳️ Requirements

• Over 3 years of professional software engineering experience, with a strong focus on recent Python development for production systems.

• Experience in building LLM-powered or agentic systems utilizing frameworks like LangChain, LangGraph, or similar, including tool calling, orchestration, and managing agent states.

• Strong design instincts, emphasizing clean, testable code and effective component design.

• Comprehensive understanding of modern async Python, API and service design, and relational databases, particularly PostgreSQL.

• Proven experience in delivering cloud-native systems using Azure or a similar platform, CI/CD practices, and Docker; familiarity with Kubernetes is a plus.

• Bachelor’s degree in Computer Science, Engineering, or a related field, or equivalent experience.

• Proficiency in English for effective technical communication.

• Preferred: experience with Deep Agents, multi-agent/subagent architectures, agent memory, or human-in-the-loop methodologies.

• Preferred: knowledge of Model Context Protocol (MCP) or agent-to-agent (A2A) interoperability.

• Preferred: experience with RAG and retrieval systems, citation practices, and evaluating LLM output quality.

• Preferred: familiarity with LLM observability and tracing tools, including MLflow and OpenTelemetry, as well as evaluations for safe model upgrades.

• Preferred: experience with infrastructure-as-code using Pulumi or Terraform.

🏝️ Benefits

• Competitive salary.

• Comprehensive benefits package.

• Flexible time off (DTO).

• Parental leave.

• Equity program.

• Annual performance bonus.

• Long-term incentive opportunities.

• Opportunities for growth and ownership.

• Commitment to knowledge sharing and continuous improvement.

• An inclusive and diverse work environment.