Gen AI Engineer

Innovationm; Delhi; Hybrid; INR 4,000,000 - 7,000,000; Full time

Job summary

Innovationm in Noida (Hybrid) is seeking a Gen AI Engineer with 8+ years of experience to design enterprise Generative AI solutions. You will architect AI systems using Bedrock, Azure OpenAI, and related platforms, and build multi-agent, RAG-enabled pipelines that integrate with cloud-native apps and microservices.

Key focus areas include LangChain/agentic frameworks, vector stores like Pinecone/OpenSearch, and robust CI/CD that aligns with enterprise security and reliability standards.

Qualifications

• 8-10 years of overall experience in GenAI and enterprise AI systems.
• Hands-on with advanced GenAI and agentic AI concepts and frameworks.
• Deep knowledge of LangChain or a custom agentic framework design.
• Experience with Retrieval-Augmented Generation (RAG) and vector databases.
• Cloud-native deployment using AWS/Azure and integration via REST APIs.

Responsibilities

• Design and develop enterprise Generative AI solutions across cloud platforms.
• Define AI solution architectures, patterns, and deployment strategies.
• Build autonomous multi-agent systems with tool-calling and routing.
• Implement optimized RAG pipelines and vector search for fast retrieval.
• Create CI/CD pipelines and integrate AI components with cloud-native apps.

Skills

GenAI & Agentic AI

LangChain

RAG pipelines

Cloud platforms (AWS/Azure)

RESTful APIs & microservices

Tool integration & function calling

Tools

Amazon Bedrock

Azure OpenAI Service

Azure AI Foundry

Groq

OpenSearch

Pinecone

Qdrant

Job description

Role: Gen AI Engineer

Experience: 8+ Years

Preferred Skills: RAG, Langchain, Agentic AI, AWS, Agent Core

Location: Noida (Hybrid)

Role & responsibilities:

• Design and develop enterprise Generative AI solutions using Amazon Bedrock, Azure OpenAI Service, Azure AI Foundry, Grog, or AI Search Index platforms.
• Define AI solution architectures and implementation approaches aligned with business and technical objectives.
• Define technical solution architectures, design patterns, and deployment strategies aligned with business goals, reliability standards, and enterprise security policies.
• Design autonomous multi-agent systems, tool-calling pipelines, dynamic routing mechanisms, and complex multi-step reasoning frameworks.
• Implement optimized Retrieval-Augmented Generation (RAG) pipelines, semantic search, vector databases, and indexing models for fast and accurate information retrieval.
• Build enterprise-ready CI/CD pipelines and integrate AI components seamlessly with cloud-native applications and existing IT ecosystems.
  

Requirements

• 8-10 years of overall Experience.
• Strong Hands-on experience with Advanced GenAI & Agentic AI
  Deep practical knowledge of LangChain or custom agentic framework design.
• Hands on experience with Retrieval-Augmented Generation (RAG)
• Hands-on expertise with Amazon Bedrock, Azure OpenAI Service, Azure AI Foundry, Groq, and custom AI Search indexes.
• Strong domain knowledge in Retrieval-Augmented Generation (RAG), embeddings, vector databases (e.g., Pinecone, Qdrant, OpenSearch), prompt engineering, and function calling / tool integration.
• Proficiency in cloud-native application deployment (AWS / Azure), RESTful APIs, microservices architecture, and enterprise application integration patterns.