Generative AI Engineer

Maven Workforce Inc.; Chennai District; On-site; INR 4,000,000 - 7,000,000; Full time

Job summary

Maven Workforce Inc. seeks a Senior AI Engineer with 8–25 years of AI experience and 3–4 years building deployable AI solutions.

You will design, develop, and deploy AI systems leveraging LLMs, knowledge graphs, and RAG techniques to enable conversational intelligence and automation. You will work across data, engineering, and product teams to deliver production-grade GenAI applications, using frameworks like LangChain and Azure AI services, with strong emphasis on governance, observability, and

Qualifications

• 8-25 years of AI/ML experience with 3-4 years deploying AI solutions.
• Strong expertise in Agentic AI, Generative AI, LLMs, SLMs, RAG and ML pipelines.
• Experience converting business problems into technical AI solutions.

Responsibilities

• Design, build, and optimize end-to-end AI systems using LLMs and ML models.
• Develop GenAI-powered apps with LangChain, LangGraph, LangSmith, Langfuse, LlamaIndex.
• Develop Knowledge Graphs and Graph RAGs for grounded AI solutions.
• Implement advanced RAG pipelines with vector DB and semantic/hybrid search.
• Engineer prompts, templates, and chains for performance and reasoning.
• Work with REST APIs and API integration across stacks.
• Design multi-agent orchestration systems for cross-task collaboration.
• Deploy models using Azure ML and Azure OpenAI.
• Collaborate with product, data, and engineering teams.
• Maintain documentation, experiment tracking, and DevOps practices.

Skills

LLMs experience

Graph DBs

Python ML

Azure AI

REST APIs

CI/CD

Tools

LangChain

LangGraph

LangSmith

Langfuse

LlamaIndex

Neo4j

Azure OpenAI

Cognitive Services

Docker

Kubernetes

MLflow

FastAPI

Streamlit

Azure ML

Job description

Job Title: Senior AI Engineer (Generative AI, Agentic AI, Knowledge Graphs, LLMs, RAG &ML) Experience: 8–25 Years

Role Overview

We are looking for a highly skilled AI Engineer with 8-25 years of experience and at least 3-4 years of experience in building and deploying AI solutions, with strong expertise in Agentic AI, Generative AI, LLMs, SLMs, Retrieval-Augmented Generation (RAG), and traditional Machine Learning pipelines, Knowledge Graphs and passionate about building intelligent, GenAI applications. In this role, you’ll convert business problem into technical AI solutions, gather requirements, design, develop, and deploy AI systems to enable conversational intelligence, reasoning, and automation capabilities. The ideal candidate should be comfortable working across structured and unstructured data, ML, and software engineering layers, leveraging frameworks like LangChain, Azure AI Foundry, A2A, MCP, Neo4J and Azure OpenAI to build scalable, agentic AI applications using python. You’ll have the opportunity to be part of AI-driven change management, driving greater impact through efficiency, cost savings, and innovation.

Responsibilities

• Design, build, and optimize end-to-end AI systems leveraging both LLMs and classical ML models.
• Develop GenAI-powered applications using frameworks such as LangChain, LangGraph, LangSmith, Langfuse, LlamaIndex and agentic architectures for workflow automation, with observability and traceability.
• Develop Knowledge Graphs & leverage Graph DBs and Graph RAGs to implement grounded AI solutions.
• Implement advanced RAG pipelines — including document chunking, vector database integration, semantic search and hybrid search. Experience in RAG optimization techniques (query rewriting, reranking, memory-augmented approaches).
• Engineer and refine prompts, system templates, and chains for performance, consistency, and contextual reasoning.
• Work with Rest APIs, well-versed in API integration with any stack UI.
• Design and manage multi-agent orchestration systems that interact and collaborate across tasks.
• Develop, evaluate, and deploy traditional ML models using Python, Pandas, NumPy, Scikit-learn, and other libraries.
• Work closely with data engineers to ensure data readiness, feature engineering, and model lifecycle governance.
• Deploy models using Azure ML, Azure OpenAI, Cognitive Services, and other Azure AI offerings.
• Collaborate with product, data, and engineering teams to deliver production-grade AI solutions.
• Maintain strong documentation, experiment tracking, and best practices in version control and well versed with DevOps lifecycles.

Required Skills

• LLMs: Experience working with multiple models (OpenAI GPT, Claude, Gemini, Mistral, Llama, etc.)
• Knowledge Agents: Neo4j, GraphRAG, Cipher Query, other compatible Graph DBs
• Data Background: Knowledge Graphs, Graph DB, Strong SQL, data engineering, ETL, preparation, transformation, and feature engineering skills
• Azure Cloud Ecosystem: GIT, Devops pipelines, Azure AI Services, Azure OpenAI, Cognitive Search, Azure AI Foundry, and related services
• APIs & Integration: REST APIs, FastAPI, Streamlit (optional), or similar frameworks
• Versioning & Deployment: Git, CI/CD, MLflow (preferred)

Preferred Skills

• Experience with LLM fine-tuning, perform fine-tuning or adapter-based training (LoRA, PEFT, etc.) on domain-specific data when needed.
• Development Familiarity with front-end or back-end frameworks (FastAPI, Streamlit, React) to build AI-powered tools.
• Hands-on experience with Azure DevOps, Kubernetes, or Docker.
• Familiarity with enterprise AI governance, access control, IAM and cost optimization in cloud setups.