Senior AI Engineer

We are seeking a Senior AI Engineer / GenAI Full-Stack Developer to lead the architecture, engineering, and deployment of enterprise-grade Generative AI products and agentic applications. In this role, you will bridge modern full-stack application development in JavaScript/TypeScript, Node.js, and React with cutting-edge Large Language Model (LLM) integrations, Retrieval-Augmented Generation (RAG) pipelines, and autonomous agent workflows., Full-Stack & AI Application Development: Architect and build production-grade web applications, digital platforms, and AI copilots using TypeScript, Node.js, React, and React Native. Agentic Workflows & Multi-Agent Orchestration: Design, implement, and support stateful AI agents, multi-step reasoning systems, and task automation solutions using frameworks such as LangGraph, LangChain, Semantic Kernel, CrewAI, or AutoGen. LLM Integration & API Architecture: Build and consume REST APIs to integrate applications with foundation models (Azure OpenAI, AWS Bedrock, Google Vertex AI) and enterprise business systems. Enterprise RAG & Knowledge Retrieval: Develop end-to-end RAG pipelines utilizing embeddings, vector databases (Pinecone, FAISS, OpenSearch, PGVector), hybrid search, and semantic retrieval to ground model outputs in enterprise data. LLM Evaluation & Observability: Implement AI evaluation frameworks, quality benchmarks, hallucination detection, response scoring mechanisms, and cost/latency monitoring. Production Engineering: Maintain automated CI/CD pipelines, source control practices, unit/integration testing, monitoring, and production troubleshooting across application, model, and platform layers.

Experience: 8+ years of software engineering experience, including strong hands-on development in JavaScript/TypeScript, with recent experience building and supporting Generative AI/LLM applications in production. Full-Stack Mastery: Strong hands-on expertise with Node.js, React, React Native, JavaScript, and TypeScript. GenAI Concepts: Deep understanding of Prompt Engineering, RAG, AI Agents, Tool/Function Calling, Context Management, and LLM Evaluation. API & Systems Integration: Proven track record building and consuming RESTful APIs to integrate AI services with enterprise data sources and business platforms.

Preferred Qualifications Experience working on a shared Enterprise AI Platform or building centralized GenAI microservices. Hands-on development with AI orchestration frameworks: LangGraph, LangChain, Semantic Kernel, CrewAI, or AutoGen. Experience with cloud AI platforms such as Azure OpenAI, Azure AI Services, AWS Bedrock, or Google Vertex AI. Familiarity with vector search architectures, hybrid search, and prompt versioning tools.