Description

You will architect and build scalable Gen-AI applications and APIs, owning the full development lifecycle from design to deployment.

This role is remote.

Responsibilities

• Develop high-performance AI APIs and backend services using Python, FastAPI, and asynchronous programming.
• Implement RAG systems, vector search, and retrieval strategies using LLMs, LangChain, and PyTorch.
• Design and deploy cloud-native applications on AWS using Docker and modern JavaScript frameworks.
• Conduct code reviews, architecture design, and mentor junior engineers to ensure system reliability and security.
• Monitor AI system performance, optimizing for latency, cost, and accuracy while implementing safety guardrails.

Required Skills

• 5+ years of experience in software applications development and systems analysis.
• Strong proficiency in Python, FastAPI, SQL, and JavaScript frameworks (React, Angular, or Vue).
• Hands-on experience with Large Language Models (OpenAI, Gemini, Llama) and Gen-AI frameworks like LangChain and LangGraph.
• Experience building RAG systems and working with vector databases (PostgreSQL + pgvector, Pinecone, FAISS).
• Proficiency with Docker, AWS, and PyTorch for model development and deployment.
• Solid understanding of prompt engineering, workflow orchestration, and stateful AI applications.

Preferred Skills

• Experience with multi-agent systems, LlamaIndex, Hugging Face, and advanced retrieval strategies like re-ranking.
• Familiarity with GCP or Azure cloud providers and monitoring/observability tools for AI governance.

Key Skills

Education

Any Graduate