Description

You will architect and implement agentic AI systems, designing multi-agent collaboration models to solve complex business problems.

This role is on-site.

Responsibilities

• Design and build reusable tools, APIs, and memory architectures for agent coordination and contextual awareness.
• Lead hands-on development and deployment of GenAI applications, including assistants, copilots, and decision-support systems.
• Evaluate and integrate LLM capabilities, focusing on retrieval-augmented generation (RAG) and tool-usage patterns.
• Optimize agent performance for real-time use cases, ensuring scalability, reliability, and adherence to ethical constraints.
• Manage cost optimization strategies, including API usage, latency tuning, and autoscaling for production systems.

Required Skills

• 9-14 years of experience in software engineering or AI/ML domains.
• Minimum 2-3 years of hands-on experience with Generative AI, LLMs, and multi-agent systems.
• Strong proficiency with AWS and cloud-based AI deployments.
• Deep expertise in LangChain or similar LLM orchestration frameworks.
• Proven experience building and deploying production-grade GenAI applications.
• Strong understanding of prompt engineering, RAG, and LLM-based architectures.
• Experience with API integrations and scalable system design.
• Ability to drive architecture, mentor teams, and lead technical decision-making.

Preferred Skills

• Experience with ChatGPT and OpenAI APIs.
• Track record of leading architectural discussions, PoCs, and iterative solution development.

Key Skills

Education

Any Graduate