Agentic AI Engineer

Experience5 to 7 Years

KEY RESPONSIBILITIES

Design, develop, and deploy machine learning and generative AI models tailored to business use cases.

Build and optimize chatbots and conversational AI systems using LLMs and modern conversational frameworks.

Implement RAG-based (Retrieval-Augmented Generation) architectures for intelligent, context-aware information retrieval.

Develop, iterate, and fine-tune prompt engineering strategies to maximize LLM application performance.

Design and build agentic AI workflows including autonomous agents, tool-use pipelines, and multi-agent systems.

Work with AWS cloud services for solution deployment, monitoring, and auto-scaling.

Collaborate with cross-functional teams (product, data, DevOps) and serve as a direct technical liaison with clients.

Build and maintain CI/CD pipelines (GitHub Actions, Jenkins) for seamless model deployment and updates.

Ensure production-grade model performance, scalability, reliability, and observability.

Mentor junior team members and contribute to best practices across the AI engineering team.

REQUIRED SKILLS & EXPERIENCE Core AI / ML

Hands-on experience building and deploying Agentic AI systems (Must-Have).

Strong, production-grade proficiency in Prompt Engineering for LLM-based applications (Must-Have).

Experience designing RAG architectures (vector databases, embeddings, semantic search).

Chatbot and conversational AI development using frameworks such as LangChain, LlamaIndex, or similar.

Solid understanding of machine learning concepts, model evaluation, and deployment workflows.

Programming & Tools

Strong Python proficiency—NumPy, Pandas, Scikit-learn, and AI/ML libraries.

Intermediate-level experience with AWS cloud services.

CI/CD pipeline experience — GitHub Actions.