Responsibilities
1. Develop Intelligent Autonomous Agents
- Build multi-step reasoning agents using frameworks such as LangGraph, OpenAI Assistants, LangChain, or custom orchestrators
- Implement agent behavior that adapts to structured business rules, data context, and operational constraints
- Design workflows that allow agents to interact with internal tools, APIs, and datasets securely and reliably
- Ensure agents operate with predictable logic, proper guardrails, and clear decision boundaries
2. Design Context-Driven AI Architectures
Structure the information, rules, and environment agents rely on to perform accurate actions
- Build reusable context layers, memory strategies, evaluation components, and tool interfaces
- Work with cross-functional teams to convert business processes into well-defined context schemas and agent behaviors
3. Integrate Agents into Core Systems
- Connect agents with internal services, workflow engines, monitoring tools, and operational platforms
- Implement safe-action mechanisms, sandboxing, and auditability for higher-risk workflows
- Collaborate with engineers to deploy and maintain agents in production environments
4. Build Internal Tooling for Agent Reliability
- Develop libraries, testing utilities, simulation frameworks, and automated evaluation tooling
- Maintain performance, reliability, and versioning for agent-related components
- Diagnose agent behavior and optimize reasoning consistency, latency, and observability
Requirements
- Hands-on experience with LLM APIs, agent frameworks, vector stores, and retrieval pipelines
- Understanding of orchestrators, tool-calling systems, context modeling, and multi-step reasoning
- Ability to translate complex workflows into structured, machine-actionable logic
- Experience building autonomous agents or workflow automation systems
- Knowledge of event-driven architectures, distributed systems, or API integration
- Contributions to AI/LLM tooling, frameworks, or open-source projects
