Description

You will build, fine-tune, and deploy AI-driven features using Large Language Models (LLMs).

Responsibilities

• Design and maintain applications powered by models like GPT-4, Claude, or Llama 3.
• Develop and optimize Retrieval-Augmented Generation (RAG) pipelines to ground AI responses in private data.
• Iterate on complex prompt templates and chains to improve accuracy, safety, and performance.
• Build robust APIs and microservices connecting AI capabilities with core products.
• Implement evaluation frameworks (e.g., Ragas, TruLens) to mitigate hallucinations and ensure output quality.

Required Skills

• Expert proficiency in Python or TypeScript.
• Deep experience with orchestration tools like LangChain, LlamaIndex, or Haystack.
• Proficiency in web frameworks such as FastAPI, Flask, or Django.
• Understanding of embeddings, tokenization, and vector similarity search.
• Experience deploying applications on AWS, Azure, or GCP.
• Familiarity with Docker.

Key Skills

Education

Any Graduate