Description

You will build and deploy LLM-powered applications for text generation, summarization, QA, conversational AI, and enterprise knowledge search.

This role is on-site.

Responsibilities

• Develop RAG pipelines using embeddings, vector databases, and grounding techniques with enterprise data.
• Implement Azure OpenAI, Cognitive Search, and related services to create secure, compliant GenAI solutions.
• Integrate LLMs into backend applications, microservices, and enterprise platforms for seamless deployment.
• Optimize prompts, system instructions, and orchestration patterns to ensure quality, reliability, and cost efficiency.

Required Skills

• 5+ years of experience in AI/ML and Python development.
• Hands-on experience building RAG pipelines.
• Proficiency with Azure OpenAI, LLMs, and Vector Databases.
• Experience with Azure Data Lake, Azure Data Factory, and Databricks.
• Understanding of embeddings, knowledge bases, and grounding techniques.
• Ability to design microservices integration and orchestration patterns.

Preferred Skills

• Experience with prompt optimization and system instructions.
• Background in conversational AI applications.

Key Skills

Education

Any Graduate