Description

Build and optimize Generative AI solutions, including LLM integration, RAG pipelines, and cloud deployment.

This role is on-site.

Responsibilities

• Develop GenAI solutions using LLMs, handling prompt design, response logic, and evaluation.
• Build RAG pipelines that retrieve relevant context and generate grounded answers.
• Integrate AI components with data sources and application services for end-to-end functionality.
• Implement quality and safety checks, including relevance and grounding validation for outputs.
• Optimize latency and cost for LLM/RAG workflows and support deployment to cloud environments.

Required Skills

• 7-12 years of relevant experience in software or AI engineering.
• Strong expertise in Generative AI (GenAI) and Large Language Models (LLMs).
• Hands-on experience building and managing Retrieval-Augmented Generation (RAG) systems.
• Proficiency in AI model evaluation, reliability testing, and performance optimization.
• Experience with production deployment of AI services.
• Cloud platform knowledge (AWS or Azure).
• Strong problem-solving and analytical abilities.

Preferred Skills

• Experience with prompt engineering techniques.

Key Skills

Education

Any Graduate