Description

Design and implement enterprise-grade GenAI and agentic AI solutions, owning the end-to-end architecture from model selection to production deployment.

This role is on-site.

Responsibilities

• Design and build agentic architectures featuring planning, tool use, memory, and multi-agent coordination.
• Develop Retrieval-Augmented Generation (RAG) systems using vector databases and semantic search.
• Fine-tune, evaluate, and optimize LLMs for enterprise-specific tasks, focusing on hallucination mitigation.
• Integrate GenAI capabilities into microservices and APIs, ensuring scalability, observability, and cost efficiency.
• Mentor junior engineers and establish best practices for Responsible AI, security, and data privacy.

Required Skills

• 10+ years of software engineering experience with strong proficiency in Python (mandatory).
• Hands-on experience with LLMs, GenAI frameworks, and LangChain-style orchestration.
• Deep understanding of Agentic AI concepts: planner, executor, evaluator, and reasoning chains.
• Experience with vector databases, semantic search, and prompt engineering/orchestration.
• Proficiency in cloud platforms (Azure, AWS, or GCP) and microservices architecture.
• Solid grasp of NLP, deep learning, transformer-based models, and model evaluation metrics.

Preferred Skills

• Exposure to Java or TypeScript.
• Experience with agent memory, self-reflection mechanisms, and feedback loops.

Key Skills

Education

Any Graduate