Description

Build AI-powered applications and conversational agents using LLMs and vector databases.

This role is on-site.

Responsibilities

• Design and build AI applications using LLMs to interface with SQL databases and Snowflake.
• Develop and integrate Retrieval Augmented Generation (RAG) pipelines using vector databases.
• Build conversational workflows using AI orchestration frameworks.
• Implement natural language-to-SQL or data-querying capabilities.
• Support deployment, monitoring, and optimization of AI applications following MLOps practices.

Required Skills

• 3–5 years of hands-on experience in AI/ML or applied GenAI development.
• Strong Python programming skills, including building backend services or APIs.
• Hands-on experience with LLMs and GenAI APIs (OpenAI, Azure OpenAI, etc.).
• Practical experience with RAG concepts, embeddings, and vector databases.
• Experience querying structured databases like Postgres, MySQL, or Snowflake.
• Familiarity with Git, code reviews, and basic CI/CD concepts.
• Strong problem-solving abilities.

Preferred Skills

• Exposure to AI orchestration frameworks like LangChain or LlamaIndex.
• Experience deploying applications on AWS or Azure.

Key Skills

Education

Any Gradute