AI Engineer (Node.js / TypeScript)

About the job

Role Overview

We are looking for an AI Engineer with hands-on experience in building GenAI-powered applications, agentic workflows, and RAG-based chatbots using TypeScript. The ideal candidate should also have strong backend engineering skills in Node.js. You will be responsible for designing, developing, and deploying AI-driven features end-to-end, managing evaluation workflows, building scalable services, and working closely with product and engineering teams to ship high-quality AI capabilities.

Key Responsibilities

• Design, build, and manage agentic workflows (multi-step reasoning, tool usage, automation flows).
• Build, optimize, and maintain RAG-based chatbots, including embeddings, retrieval, ranking, and context management.
• Develop AI-powered product features end-to-end in TypeScript, from data ingestion to API deployment.
• Create and manage AI feature evaluation workflows, including metrics, test harnesses, and continuous improvement loops.
• Build and integrate AI/ML models into production-grade Node.js applications.
• Develop backend services, workflows, and APIs for AI-driven capabilities.
• Work with vector stores, embeddings, LLM APIs, inference pipelines, and structured/unstructured data.
• Implement data preprocessing, feature extraction, and model evaluation logic.
• Build scalable microservices to support AI workloads (inference, automation, monitoring).
• Optimize performance, latency, and reliability of AI endpoints and pipelines.
• Collaborate with product managers to translate business needs into technical solutions.
• Maintain clean documentation, testing, and high-quality, maintainable code.

Requirements

• 1.5+ years of experience building GenAI-powered applications, agentic workflows, and RAG-based chatbots using TypeScript.
• Strong hands-on experience in Node.js / TypeScript backend development.
• Strong understanding of ML concepts + hands-on experience with:
• embeddings, transformers, vector search, LLM integration
• RAG architectures and retrieval pipelines
• Good understanding of machine learning, deep learning, and NLP fundamentals.
• Experience using OpenAI, Anthropic, Groq, Google Vertex AI, Hugging Face, or similar GenAI tools and APIs.
• Experience with relational and NoSQL databases (PostgreSQL, MongoDB) and vector databases like Pinecone/Qdrant.
• Familiarity with Docker, REST APIs, microservices, and cloud deployment (AWS/GCP optional).
• Solid debugging, profiling, and backend optimization skills.

Backend engineering fundamentals such as:

• event-driven architecture
• queue systems (e.g., RabbitMQ, Kafka, SQS)
• authentication/authorization flows
• API rate limiting, caching, CI/CD.