Description

You will build and deploy production-grade AI systems, including LLM integrations, RAG pipelines, and intelligent agents.

This role is on-site.

Responsibilities

• Develop prompt-driven systems and AI agents using LLMs and retrieval-augmented generation (RAG) techniques.
• Integrate AI models into applications via approved APIs and SDKs.
• Conduct model evaluation, prompt tuning, and experimentation to optimize accuracy and quality.
• Apply responsible AI principles, addressing security, privacy, explainability, and bias mitigation.
• Deploy and operate applications in cloud environments using CI/CD pipelines.

Required Skills

• 16+ years of experience in software engineering or ML operations.
• Deep understanding of LLMs, prompt engineering, and RAG architectures.
• Proficiency in integrating models via APIs and SDKs.
• Experience with CI/CD pipeline deployment and cloud infrastructure.
• Strong grasp of Agile methodologies and effective communication.
• Knowledge of responsible AI practices including bias mitigation and security.

Preferred Skills

• Experience with open-source and enterprise-approved AI tooling.
• Background in model evaluation frameworks and experimentation.

Key Skills

Education

Any Gradute