Description

You will build and deploy generative AI applications, owning the full lifecycle from API design to model monitoring.

This role is hybrid.

Responsibilities

• Implement complex solutions using extensive Python programming.
• Design and develop secure, scalable RESTful APIs using Python-FastAPI.
• Develop and deploy LLM-based applications, managing data processing for structured and unstructured datasets.
• Own the integration of Retrieval-Augmented Generation (RAG) using vector databases.
• Scale and monitor machine learning models, specifically LLMs, in live environments.

Required Skills

• 5+ years of professional experience in software development.
• Expert proficiency in Python.
• Proven experience with Large Language Models (LLMs) and third-party providers like OpenAI and Anthropic.
• Hands-on experience with RAG implementation and vector databases.
• Proficiency in Git for version control and collaborative workflows.
• Familiarity with cloud infrastructure including AWS, Azure, and GCP.
• Skilled in RESTful API design and development.
• Experience with prompt engineering, function calling, and conversational AI.

Key Skills

Education

Any Graduate