Description

You will design and deploy large language model applications, focusing on RAG architectures and agentic frameworks.

This role is on-site.

Responsibilities

• Build, tune, and deploy LLM-based applications using Vertex AI and Hugging Face.
• Implement advanced Retrieval-Augmented Generation (RAG) pipelines and techniques.
• Develop agentic framework-based use cases and reusable prompt templates.
• Integrate Google Gemini, OpenAI, Anthropic Claude, Mistral, and Llama models.
• Apply guardrails and safety methodologies to assess GenAI feature performance.

Required Skills

• 6+ years of hands-on experience in Core AI/ML Foundations.
• Strong background in Machine Learning, Data Science, Statistics, and NLP.
• Deep working knowledge of Neural Networks and Large Language Models (LLMs).
• Proven expertise in prompt engineering, prompt tuning, and strategy development.
• Hands-on experience with open-source LLMs (Llama, Mistral) and proprietary models.
• Ability to implement guardrails for AI safety and performance assessment.

Preferred Skills

• Experience with advanced RAG techniques beyond basic implementations.
• Background in deploying production-grade GenAI features at scale.

Key Skills

Education

Any Gradute