we are seeking a highly skilled Senior AI Engineer to design and implement complex, multi-agent systems powered by LLMs.
In this role, you will build and orchestrate AI agents using LangGraph and LangChain, manage stateful conversations, and support scalable RAG pipelines that connect external knowledge sources to reasoning agents. Youll work closely with product and backend teams to deliver real, production-grade AI capabilities.
Responsibilities:
Agent Orchestration: Design, build, and maintain networks of LLM-powered agents that collaborate, share context, and reason together to execute complex workflows.
LangGraph Architecture: Implement and manage LangGraph graphs that handle message memory, context persistence, and multi-step task coordination.
RAG Pipelines: Optimize RAG systems to enrich agent reasoning with relevant, up-to-date information.
Prompt & API Composition: Build modular prompt templates and API calls that agents use for reasoning, retrieval, and action execution.
Integration & Deployment: Work with engineers to integrate the agentic framework into production systems via APIs and backend services.
Evaluation & Iteration: Implement evaluation frameworks to measure performance, reliability, and consistency of AI responses across multi-agent pipelines.
Cross-Team Collaboration: Partner with product and engineering teams to align AI behaviors with real user workflows and KPIs.
In this role, you will build and orchestrate AI agents using LangGraph and LangChain, manage stateful conversations, and support scalable RAG pipelines that connect external knowledge sources to reasoning agents. Youll work closely with product and backend teams to deliver real, production-grade AI capabilities.
Responsibilities:
Agent Orchestration: Design, build, and maintain networks of LLM-powered agents that collaborate, share context, and reason together to execute complex workflows.
LangGraph Architecture: Implement and manage LangGraph graphs that handle message memory, context persistence, and multi-step task coordination.
RAG Pipelines: Optimize RAG systems to enrich agent reasoning with relevant, up-to-date information.
Prompt & API Composition: Build modular prompt templates and API calls that agents use for reasoning, retrieval, and action execution.
Integration & Deployment: Work with engineers to integrate the agentic framework into production systems via APIs and backend services.
Evaluation & Iteration: Implement evaluation frameworks to measure performance, reliability, and consistency of AI responses across multi-agent pipelines.
Cross-Team Collaboration: Partner with product and engineering teams to align AI behaviors with real user workflows and KPIs.
Requirements:
4+ years of experience as a Node.js (TypeScript) backend developer.
1+ years as an AI Engineer
Experience integrating LLM pipelines and external APIs.
Strong understanding of system design, performance tuning, and reliability engineering.
Strong expertise in distributed systems, microservices, event-driven architectures, and scalable APIs.
Experience deploying and monitoring systems in production environments.
Experience with using LangGraph / LangChain or similar frameworks.
Python and MongoDB are an advantage.
4+ years of experience as a Node.js (TypeScript) backend developer.
1+ years as an AI Engineer
Experience integrating LLM pipelines and external APIs.
Strong understanding of system design, performance tuning, and reliability engineering.
Strong expertise in distributed systems, microservices, event-driven architectures, and scalable APIs.
Experience deploying and monitoring systems in production environments.
Experience with using LangGraph / LangChain or similar frameworks.
Python and MongoDB are an advantage.
This position is open to all candidates.
