AI Engineer

Role Overview

Experience - 3-8 Years

Location - Hyderabad/Indore/Ahmedabad

Onsite

We are looking for a hands-on Applied AI Engineer to build and maintain components of an enterprise-grade, multi-agent AI platform. The ideal candidate has 3–5+ years of software engineering experience with strong Python skills, practical experience building GenAI/LLM-powered applications, and the ability to implement agent logic, RAG pipelines, and integrations under the architectural direction of the AI Architect. The role requires close collaboration with the Business Analyst, Integration Engineer, DevOps Engineer, and QA teams to deliver a secure, auditable, and production-ready document intelligence system.

Experience

Strong focus on implementation, delivery, and problem-solving in production environments

Key Responsibilities

Agent & AI Application Development

• Build and maintain individual agents (e.g., Proofreader, Formatter, Document Converter, Paralegal, Reviewer/Approver, Document Router) per the architecture defined by the AI Architect.
• Implement multi-agent orchestration logic, task decomposition, tool/function calling, and inter-agent communication using frameworks such as LangChain / LangGraph.
• Build Retrieval-Augmented Generation (RAG) pipelines — document chunking, embeddings generation, and vector store integration — for grounding agent responses in SOPs, QC guidelines, and playbooks.
• Implement agent-to-tool and agent-to-system integrations using standardized protocols such as Model Context Protocol (MCP).

Required Skills & Experience

• 3–5+ years of overall software engineering experience, including at least 2 years building AI/ML, GenAI, or LLM-powered applications.
• Strong programming skills in Python Or Java with the ability to build and maintain enterprise-grade APIs, microservices, and integration layers.
• Practical experience building or contributing to multi-agent / agentic AI systems, including agent orchestration and autonomous task execution.
• Working knowledge of agent frameworks such as LangChain, LangGraph, or Semantic Kernel, and familiarity with the Model Context Protocol (MCP) for tool/data integration.
• Experience implementing Retrieval-Augmented Generation (RAG) pipelines — embeddings, chunking strategies, and vector databases (e.g., Azure AI Search, Qdrant, Pinecone, or similar).
• Familiarity with RBAC, SSO/authentication, audit logging, and secure coding practices for enterprise platforms.
• Exposure to document intelligence / document processing systems (parsing, OCR, formatting/validation engines) is desirable.
• Comfortable working with REST APIs, version control (Git), CI/CD pipelines, and Agile/Scrum delivery practices.
• Strong problem-solving skills, attention to detail, and ability to work effectively within a distributed delivery team.

What We Are Looking For

• We need professionals who can quickly understand:
• • What we are building
• • The business problems we are solving
• • The platforms and applications we are developing and supporting
• • How to implement AI solutions in real-world enterprise environments

Education

• Bachelor’s or master’s degree in computer science, Engineering, Artificial Intelligence, or a related field (or equivalent practical experience).