Description

You will design, develop, and deploy multi-agent AI systems and scalable agent-based architectures.

This role is on-site.

Responsibilities

• Design and deploy multi-agent AI systems using open-source or enterprise frameworks.
• Implement Generative AI and RAG pipelines using LangChain, LlamaIndex, or similar tools.
• Architect modular agentic AI systems using LangGraph, CrewAI, or AutoGen.
• Build APIs, microservices, or full-stack solutions to support AI capabilities.
• Ship AI-powered features into production while ensuring system reliability and scalability.

Required Skills

• 8+ years of experience in software engineering and AI development.
• Proficient in Python with strong fundamentals in OOP, design patterns, unit testing, and CI/CD.
• Hands-on experience building production-ready Generative AI applications (LLMs, RAG).
• Deep understanding of agent-based architectures, task decomposition, memory management, and reasoning loops.
• Expertise with LangChain, LlamaIndex, LangGraph, CrewAI, or AutoGen.
• Familiarity with vector databases, embedding models, and prompt engineering.
• Strong understanding of REST APIs and Cloud Platforms (AWS, GCP, or Azure).

Preferred Skills

• Experience with graph algorithms and graph-based reasoning systems.
• Familiarity with cognitive architectures or planning algorithms.
• Contributions to open-source AI projects or research publications.

Key Skills

Education

Any Graduate