Python Engineer – LangGraph / AI Agent Workflows
About the Role
We are looking for a Python Engineer to design, build, and maintain stateful AI agent workflows using LangGraph. This role focuses on workflow orchestration, checkpointing, Human-in-the-Loop (HITL) interactions, resilience patterns, and observability across agent execution paths.
The ideal candidate has strong Python development expertise, hands-on experience with LangGraph or LangChain, and a solid understanding of asynchronous and distributed workflow design.
Project Overview
Our customer is a multinational corporation with more than a century of history and operations across 180+ countries, serving more than 1 billion consumers worldwide. The organization is undertaking an ambitious initiative to introduce a new generation of Reduced-Risk Products (RRPs), supported by a large-scale digital and technology ecosystem of more than 700 applications.
Intellia's mission is to help the client engineer a comprehensive software ecosystem for a game-changing IoT product at the intersection of innovative consumer experiences and cutting-edge technology.
As a Python Engineer, you will join the Core Architecture Team and contribute to the architecture, development, and implementation of best practices across the Digital Engineering Enterprise Platform.
The Platform is a set of services and internet applications designed to accelerate software development and delivery by addressing common SDLC challenges. It provides engineering teams with access to reusable services, technologies, and practices while enabling them to develop, deploy, and operate applications in compliance with established engineering standards and best practices.
Key Responsibilities
- Design and implement AI agent workflows using Python and LangGraph.
- Build and maintain graph-based orchestration logic using nodes, edges, states, and state transitions.
- Implement workflow checkpointing and recovery mechanisms using SQLite, Redis, or PostgreSQL.
- Develop Human-in-the-Loop (HITL) workflows for approvals, escalations, reviews, and intervention scenarios.
- Design resilient execution patterns, including retries, timeouts, fallbacks, and failure recovery.
- Develop asynchronous workflow execution using Python asyncio.
- Implement OpenTelemetry tracing across orchestration layers and individual workflow steps.
- Troubleshoot workflow execution issues and optimize performance, reliability, scalability, and observability.
- Collaborate closely with platform engineering, AI engineering, and architecture teams to deliver scalable agent-driven solutions.
- Develop automated tests covering workflow reliability, state transitions, checkpointing, and recovery scenarios.
- Contribute to engineering standards, architectural guidelines, and best practices for AI agent orchestration and workflow management.
- Participate in technical discussions, design reviews, and continuous improvement initiatives.
Required Skills & Experience
- 4+ years of professional Python development experience.
- Hands-on experience with LangGraph and/or LangChain, particularly for AI agent orchestration.
- Strong understanding of LangGraph nodes, edges, graphs, and state management.
- Experience implementing checkpointing with technologies such as:
- SQLite
- Redis
- PostgreSQL
- Practical experience designing and implementing Human-in-the-Loop (HITL) workflows.
- Strong understanding of resilience patterns, including:
- Retry mechanisms
- Timeouts
- Fallback strategies
- Failure recovery
- Solid experience with asynchronous Python development and asyncio.
- Understanding of distributed and stateful workflow design.
- Experience implementing application observability and distributed tracing, preferably with OpenTelemetry.
- Strong troubleshooting, debugging, and problem-solving skills.
- Experience writing automated tests for complex workflows and state transitions.
- Strong communication and collaboration skills.
Nice to Have
- Experience integrating AI solutions with AWS Bedrock.
- Experience testing multi-agent workflows.
- Hands-on experience with LangSmith and trace visualization.
- Experience with distributed systems, event-driven architectures, or workflow orchestration platforms.
- Familiarity with cloud-native application development and enterprise-scale platforms.
- Experience working in large, complex, multinational technology environments.
Education
- Bachelor's degree in computer science, Software Engineering, Information Technology, or a related technical field.
Why This Position?
- Work on next-generation AI technology: Build sophisticated, stateful AI agent workflows using LangGraph and modern LLM technologies.
- Enterprise-scale impact: Contribute to technology platforms supporting a global organization and more than one billion consumers.
- Cutting-edge IoT initiative: Work on a high-profile IoT ecosystem combining AI, cloud, digital engineering, and innovative consumer experiences.
- Architecture exposure: Join the Core Architecture Team and contribute to enterprise-level architecture, engineering standards, and best practices.
- Engineering excellence: Work on challenging problems involving distributed systems, resilience, observability, asynchronous execution, and workflow orchestration.
- Global collaboration: Collaborate with experienced AI, platform, architecture, and engineering teams across an international environment.
- Opportunity to grow: Develop deep expertise in AI agent orchestration, LangGraph, cloud technologies, and enterprise software engineering.
Key Technologies
Python | LangGraph | LangChain | asyncio | Redis | PostgreSQL | SQLite | OpenTelemetry | AWS Bedrock | LangSmith | AI Agents | Workflow Orchestration | HITL | Distributed Systems
Seniority
Mid-Senior Level
Employment Type
Full-time
