AI Engineer – RAG & Agentic AI

IntraEdge; Hyderabad; Hybrid; INR 4,000,000 - 6,500,000; Full time

Job summary

IntraEdge in Hyderabad is seeking an experienced AI Engineer to drive Generative AI, RAG pipelines, and agentic AI initiatives. The role focuses on building production-grade AI solutions using GPT-4, Claude, and other leading LLM platforms, integrating with enterprise APIs, databases, and web technologies.

You will design scalable AI components, develop prompt strategies, and collaborate with architects, data engineers, and business stakeholders to deliver reliable, enterprise-ready AI

Qualifications

• 6+ years of software engineering and application development experience.
• Experience building RAG pipelines and LLM-powered applications.
• Strong knowledge of Prompt Engineering and LLM optimization techniques.
• Hands-on experience with Agentic AI development, AI agents, tool calling, workflow orchestration, or multi-step reasoning.
• Experience with GPT-4, Claude, or comparable LLM platforms.
• Strong programming experience in Python and at least one enterprise language (Java, C#, or Node.js).
• Strong understanding of REST APIs, JSON, SQL, and enterprise integrations.

Responsibilities

• Design, develop, and deploy scalable Generative AI and LLM-powered applications.
• Build end-to-end RAG pipelines, including ingestion, embedding, retrieval, and context management.
• Develop and optimize prompt engineering strategies for accuracy and reliability.
• Design and implement agentic AI solutions with tool calls and workflow orchestration.
• Work with GPT-4, Claude, and other foundation models for enterprise AI capabilities.
• Integrate LLMs with enterprise APIs, databases, and business applications.
• Develop AI services and backend components using Python, Java, or Node.js.
• Build APIs and application integrations using REST and JSON.
• Collaborate with architects, data engineers, and product teams to deliver production-ready solutions.

Skills

Generative AI

RAG pipelines

Prompt engineering

Agentic AI development

LLM platforms

Python

Java / C# / Node.js

REST / JSON / SQL

Education

Bachelor’s or Master’s in CS/IT/Engineering

Tools

LangChain

LangGraph

Semantic Kernel

Docker

Kubernetes

Job description

Role: AI Engineering / Generative AI / Agentic AI

Job Overview

We are looking for an experienced AI Engineer with 6+ years of software engineering experience and strong hands-on expertise in Generative AI, RAG pipelines, prompt engineering, and agentic AI development. The ideal candidate should have experience building production-grade AI solutions using models such as GPT-4, Claude, and other modern LLM platforms.

The candidate will work across AI engineering and application development, integrating LLM capabilities with enterprise applications, APIs, databases, and modern web technologies.

Key Responsibilities

• Design, develop, and deploy scalable Generative AI and LLM-powered applications.
• Build end-to-end Retrieval-Augmented Generation (RAG) pipelines, including document ingestion, preprocessing, chunking, embedding, retrieval, context management, and response generation.
• Develop and optimize prompt engineering strategies for accuracy, relevance, reliability, and consistent model behavior.
• Design and implement agentic AI solutions capable of reasoning, tool calling, task orchestration, and multi-step workflows.
• Work with LLMs such as GPT-4, Claude, and other foundation models to develop enterprise AI capabilities.
• Integrate LLMs with enterprise APIs, databases, business applications, and external services.
• Develop AI services and supporting backend components using Python, Java, or Node.js.
• Build APIs and application integrations using JSON, REST, and other modern integration technologies.
• Work with SQL databases to retrieve, analyze, and integrate structured enterprise data into AI workflows.
• Design reusable AI components, frameworks, and services that can be leveraged across multiple use cases.
• Implement appropriate evaluation, testing, monitoring, and optimization mechanisms for AI applications.
• Collaborate with architects, software engineers, data engineers, product teams, and business stakeholders to deliver production-ready solutions.
• Participate in technical design, code reviews, documentation, testing, deployment, and production support.

Required Skills & Experience

• 6+ years of software engineering and application development experience.
• Proven experience building RAG pipelines and LLM-powered applications.
• Strong knowledge of Prompt Engineering and LLM optimization techniques.
• Hands-on experience with Agentic AI development, AI agents, tool calling, workflow orchestration, or multi-step reasoning.
• Experience working with GPT-4, Claude, or comparable LLM platforms.
• Strong programming experience in Python and at least one enterprise programming language such as Java, C#, or Node.js.
• Strong understanding of REST APIs, JSON, SQL, and enterprise integrations.
• Ability to design scalable, maintainable, and secure AI-enabled applications.
• Strong problem-solving, analytical, communication, and collaboration skills.

AI/GenAI: RAG, Prompt Engineering, Agentic AI, GPT-4, Claude, LLMs

Frontend: React

Data & Integration: SQL, JSON, REST APIs

Application Development: Enterprise APIs, AI-powered applications, workflow orchestration

Good to Have

• Experience with vector databases and embedding technologies.
• Knowledge of RAG evaluation, LLM observability, and AI application testing.
• Experience with LangChain, LangGraph, Semantic Kernel, or similar AI frameworks.
• Exposure to cloud platforms such as AWS, Azure, or GCP.
• Experience with Docker, Kubernetes, and CI/CD.
• Understanding of AI security, responsible AI, data privacy, and enterprise governance.

Education

Bachelor’s or Master’s degree in Computer Science, Information Technology, Engineering, or a related technical discipline.