Description

Build and deploy AI agents, multi-agent workflows, and LLM integrations for enterprise applications.

This role is hybrid.

Responsibilities

• Develop AI agents and orchestrate multi-agent workflows for enterprise use cases.
• Implement Retrieval-Augmented Generation (RAG) solutions using vector databases and search indexes.
• Build LLM integrations with Python, focusing on tool/API calling and agent orchestration.
• Design and integrate REST APIs and microservices to enable agent interactions with external systems.
• Process unstructured data and optimize agent performance through prompt tuning and reliability enhancements.

Required Skills

• 6+ years of software development experience, with strong focus on AI/LLM applications.
• Expert-level Python development and unit testing capabilities.
• Hands-on experience building AI agents, NLP systems, or chatbot solutions.
• Proven experience implementing RAG architectures with vector databases.
• Proficiency in FastAPI or Flask for building backend services.
• Experience with REST API integration and data handling.
• Familiarity with Docker and CI/CD deployment practices.

Preferred Skills

• Experience with Git version control.
• Background in prompt engineering and output optimization.

Key Skills

Education

Any Graduate