Description

You will build and optimize scalable Retrieval-Augmented Generation (RAG) applications and LLM integrations.

This role is on-site.

Responsibilities

• Develop and maintain high-quality Python code for LLM-based applications.
• Implement data retrieval and indexing strategies from databases, APIs, and file systems.
• Build and manage retrieval indices to support RAG systems.
• Optimize LLM integration and data retrieval workflows to solve complex technical problems.
• Deploy and scale applications using cloud computing platforms.

Required Skills

• 5+ years of professional software engineering experience.
• Expertise in Python programming and its relevant libraries.
• Hands-on experience with Large Language Models (LLMs) and RAG techniques.
• Practical experience using LLM APIs and retrieval systems.
• Deep understanding of data structures and algorithms for scalable application design.
• Experience with data retrieval and indexing from diverse sources.
• Familiarity with cloud platforms including AWS, GCP, or Azure.
• Degree in any field of study.

Preferred Skills

• Experience with LangChain or Hugging Face Transformers.
• Knowledge of machine learning, deep learning, and information retrieval techniques.
• Proven track record of building production-ready applications or contributing to open-source RAG/LLM projects.

Key Skills

Education

Any Graduate