Large Language Model Engineer

About the Role

YantranIN PVT LTD is seeking an experienced engineer to design and build applications and infrastructure centered around Large Language Models (LLMs). The role focuses on leveraging cutting-edge LLM technologies to develop scalable, high-performing AI solutions.

Key Responsibilities

• Design and implement applications powered by Large Language Models.
• Integrate foundational models through various APIs to enable seamless AI capabilities.
• Architect and deploy Retrieval-Augmented Generation (RAG) systems to enhance model outputs.
• Create and refine prompt engineering and optimization methods to maximize model effectiveness.
• Conduct thorough evaluation and testing to ensure model robustness and reliability.
• Perform fine-tuning of models when required to adapt to specific use cases.
• Develop pipelines for vector search and embeddings to support advanced data retrieval.
• Build and maintain APIs and production-grade services facilitating LLM usage.
• Continuously monitor model performance metrics including accuracy, cost efficiency, and response latency.

Required Expertise

• Proficiency in working with Large Language Models.
• Strong programming skills in Python for development and automation.
• Experience with cloud LLM platforms such as OpenAI, Azure OpenAI, Anthropic, and Gemini.
• Familiarity with transformer architectures and frameworks like Hugging Face.
• Knowledge of Retrieval-Augmented Generation (RAG) techniques.
• Understanding of embeddings and vector database technologies.
• Competence using LangChain and LlamaIndex tools for application development.
• Skill in building and consuming RESTful APIs.

Additional Information

This position requires a candidate who has graduated with any degree and is ready to contribute to innovative AI solutions specializing in LLM-powered applications within an onsite environment in Chennai, India.