Full Stack AI Engineer

Role Overview

We're looking for an AI/ML Engineer who is equally comfortable building and shipping full-stack web features and building the AI/ML systems that power them. You'll work across our agent architecture and knowledge layer, from retrieval pipelines and LLM-powered agents to the web application and cloud infrastructure that put them in front of users. This is a hands-on, build-things role at an early-stage product company.

Responsibilities

• Design, build, and iterate on LLM-powered agents within our multi-agent architecture.
• Build and improve retrieval-augmented generation (RAG) pipelines including embedding generation, vector search, and retrieval quality tuning.
• Evaluate and integrate LLM APIs such as OpenAI or Anthropic.
• Build and ship features across the frontend using React and backend using Node.js/Express.
• Design and consume REST APIs and work with PostgreSQL and pgvector.
• Deploy and maintain services on cloud platforms like AWS.
• Use containerization with Docker and set up CI/CD pipelines.

Requirements

• B.Tech/B.E. in Computer Science, IT, or a related field.
• 0–2 years of hands-on experience building software.
• Working proficiency in a MERN-equivalent stack: React, Node.js, and relational databases.
• Practical exposure to AI/ML concepts: LLM APIs, embeddings, or vector search.
• Comfort with Python for ML/agent tooling.
• Exposure to deploying applications to the cloud (AWS, GCP, or Azure).
• Strong fundamentals in data structures, algorithms, and API design.

Skills

• React.js
• Node.js
• Python
• AWS
• PostgreSQL