Senior LangGraph Developer

Job Summary We are seeking a highly experienced Senior LangGraph Developer to design, build, and scale production-grade agentic systems using LangGraph. This role is hands-on and architecture-driven, focused on creating stateful, multi-agent workflows that leverage LLMs for complex decision-making, orchestration, and automation. This is not an experimental or research role. The expectation is to deliver reliable, scalable, and fault-tolerant AI systems deployed in real production environments. Key Responsibilities • Design and implement advanced LangGraph workflows with complex node logic, branching, looping, and memory management • Architect and develop stateful, multi-agent systems capable of reasoning, interaction, and adaptive behavior • Optimize LangGraph pipelines for performance, scalability, and production reliability • Integrate LangGraph workflows with external APIs, databases, and LLM platforms • Lead best practices for agentic system design, debugging, and deployment • Use graph debugging and visualization tools, including LangGraph Studio • Mentor junior developers and provide technical leadership • Collaborate with AI researchers, product managers, and engineering teams to translate concepts into robust implementations Required Skills & Experience • 8+ years of overall software engineering experience • 3–4+ years of hands-on experience with LangGraph or agentic frameworks • Expert-level Python development skills • Strong experience with asynchronous programming and graph-based computation • Deep understanding of: • LLM orchestration • Memory management strategies • Stateful agent design and execution flows • Experience working with LangChain, OpenAI, Anthropic, or similar LLM platforms • Proven ability to build production-grade agentic systems with high reliability and fault tolerance • Strong debugging skills and experience with workflow visualization tools Nice to Have • Experience designing multi-agent orchestration frameworks • Background in AI infrastructure, platform engineering, or distributed systems • Prior experience scaling LLM-driven systems in production