Full Stack

Role Overview

We are looking for a Full Stack Agentic AI Engineer passionate about building next-generation AI-native products. This role combines modern full-stack development with cutting-edge Generative AI technologies to create intelligent, autonomous applications from scratch and scale them into production.

Key Responsibilities:

• Build and ship AI-native web applications using React.js and Python.
• Design Agentic AI workflows leveraging LLMs and autonomous agents.
• Create Retrieval-Augmented Generation (RAG) applications with vector databases and enterprise knowledge sources.
• Own product features end-to-end, from architecture to deployment, monitoring, and optimization.
• Develop REST APIs and backend services for AI-powered apps.
• Integrate models from OpenAI, Anthropic, Gemini, or open-source LLMs.
• Work with vector databases like Pinecone, Weaviate, Chroma, FAISS, Milvus.
• Implement prompt engineering, tool calling, memory management, and multi-agent orchestration.
• Optimize apps for latency, cost, reliability, and scalability.

Technical Requirements:

Frontend: Strong React.js/TypeScript experience; HTML5/CSS3; State management (Redux/Zustand).

Backend: Proficiency in Python with FastAPI, Flask, or Django; Microservices architecture.

AI & LLMs: Generative AI expertise; RAG pipelines; Embeddings/semantic search; LangChain/LangGraph/CrewAI experience;

• Databases: SQL/NoSQL and Vector databases (Pinecone, Chroma).