Description

You will lead the end-to-end development and implementation of Generative AI solutions, from architecture to production deployment.

This role is on-site.

Responsibilities

• Architect and oversee agent orchestration frameworks using LangChain, LangGraph, AutoGen, and Crew.ai.
• Build and manage Retrieval-Augmented Generation (RAG) and Tool-Augmented Generation (TAG) pipelines.
• Design, optimize, and govern prompt engineering strategies and reusable prompt templates for LLMs.
• Mentor team members and provide technical leadership on Gen AI architecture and best practices.

Required Skills

• 8-13 years of overall experience in software engineering, data platforms, or AI/ML-driven systems.
• 4+ years of hands-on experience with AI/ML solutions, including recent Generative AI work.
• Proven experience deploying Large Language Model (LLM)-based applications in production.
• Extensive hands-on experience with Python for AI workflows and backend services.
• Experience with agent orchestration frameworks such as LangChain, LangGraph, AutoGen, or Crew.ai.
• Solid experience building and optimizing Retrieval-Augmented Generation (RAG) pipelines.
• Practical experience integrating vector databases like Pinecone, Weaviate, or Qdrant.
• Experience leveraging cloud-native Generative AI services across AWS, Azure, and GCP.
• Hands-on experience with containerization and deployment using Docker and Kubernetes.

Preferred Skills

• Experience implementing observability, logging, and distributed tracing for AI systems.
• Knowledge of security, compliance, and data privacy considerations for LLMs.

Key Skills

Education

Any Graduate