Design, develop, and maintain scalable Node.js / TypeScript backend APIs and microservices.
Integrate LLM-based features using OpenAI, Anthropic, Cohere, Bedrock, or local LLMs (Ollama, Llama, Mistral).
Build RAG (Retrieval-Augmented Generation) workflows using vector databases (Pinecone, Weaviate, Elasticsearch, MongoDB Atlas Search, pgvector, Qdrant, etc.).
Develop and optimize ETL/Document ingestion pipelines for PDF/Doc/HTML/Text indexing.
Implement authentication and authorization flows (JWT, OAuth, Auth0, Cognito, etc.).
Work with REST / GraphQL APIs and build event-driven services (SQS, Kafka, EventBridge, RabbitMQ).
Optimize performance, reliability, and cost of AI inference workflows.
Collaborate with frontend, DevOps, and product teams for solution delivery.