AI Engineer - Generative AI / Agentic AI

About Infotel Group; Chennai District; On-site; INR 1,800,000 - 2,800,000; Full time

Job summary

About Infotel Group in Chennai, India, is seeking an AI Engineer to design, develop, and deploy production‑grade Generative AI applications and intelligent AI agents. You will leverage Python, RAG pipelines, vector databases, and orchestration frameworks to build enterprise AI solutions such as agents, copilots, and knowledge assistants.

The role requires hands‑on GenAI experience, strong Python skills, and expertise in integrating LLMs with business workflows.

Qualifications

• Hands-on Python proficiency required.
• Experience building GenAI applications and production systems.

Responsibilities

• Design and develop enterprise-grade Generative AI applications.
• Build scalable RAG (Retrieval-Augmented Generation) pipelines.
• Develop AI agents and multi-agent workflows with orchestration frameworks.
• Integrate LLMs with enterprise systems, APIs, databases and business workflows.
• Implement prompt engineering, evaluation pipelines, guardrails and AI safety mechanisms.
• Build conversational AI systems with memory and context management.
• Work with vector databases for semantic retrieval and knowledge search.
• Develop REST APIs and backend services for AI applications.
• Optimize latency, cost, scalability, and reliability of AI systems.
• Collaborate with frontend, DevOps, and business teams for production deployment.
• Participate in architecture discussions and AI innovation initiatives.

Skills

Python

LLMs / Generative AI

RAG pipelines

AI agents

Prompt engineering

Conversational AI

Tool calling

Education

Bachelor’s or Master’s in CS/AI/Data Science or related field

Tools

LangChain

LangGraph

LlamaIndex

CrewAI

AutoGen

OpenAI SDK

Anthropic SDK

Job description

AI Engineer – Generative AI / Agentic AI

Location: Chennai, India

Experience: 3–7 Years

Employment Type: Full-Time

About the Role

We are looking for a hands‑on AI Engineer to design, develop, and deploy production‑grade Generative AI applications and intelligent AI agents. The ideal candidate should have strong Python engineering skills and practical experience building LLM‑powered systems using RAG pipelines, vector databases, orchestration frameworks and cloud AI platforms.

You will work on enterprise AI solutions including conversational AI, document intelligence, AI copilots, agentic workflows, knowledge assistants and AI automation platforms.

Key Responsibilities

• Design and develop enterprise‑grade Generative AI applications
• Build scalable RAG (Retrieval‑Augmented Generation) pipelines
• Develop AI agents and multi‑agent workflows using modern orchestration frameworks
• Integrate LLMs with enterprise systems, APIs, databases and business workflows
• Implement prompt engineering, evaluation pipelines, guardrails and AI safety mechanisms
• Build conversational AI systems with memory and context management
• Work with vector databases for semantic retrieval and knowledge search
• Develop REST APIs and backend services for AI applications
• Optimize latency, cost, scalability, and reliability of AI systems
• Collaborate with frontend, DevOps, and business teams for production deployment
• Participate in architecture discussions and AI innovation initiatives

Required Skills

Core AI / GenAI Skills

• Strong hands‑on experience with Python
• Experience with LLMs and Generative AI applications
• Practical implementation experience in:

• RAG pipelines
• AI agents / Agentic AI
• Prompt engineering
• Conversational AI
• Tool calling and workflow orchestration

Frameworks & Libraries

• Experience in one or more:

• LangChain
• LangGraph
• LlamaIndex
• CrewAI
• AutoGen
• OpenAI SDK / Anthropic SDK

Vector Databases

• Experience with:

• ChromaDB
• Pinecone
• FAISS
• Weaviate
• Milvus

Backend & APIs

• FastAPI / Flask
• REST APIs
• Async programming
• Webhooks and integrations

Cloud & Deployment

• Experience in one or more:

• AWS Bedrock
• Azure OpenAI
• Google Vertex AI
• OpenAI APIs
• AWS / Azure / GCP

Additional Preferred Skills

• Docker & Kubernetes
• CI/CD pipelines
• Monitoring & observability
• PostgreSQL / DynamoDB / MongoDB
• Knowledge Graphs / GraphRAG
• Multimodal AI systems
• AI evaluation frameworks
• MCP / AI tool ecosystem

Qualifications

• Bachelor’s or Master’s degree in Computer Science, AI, Data Science, or related field
• 3+ years of software engineering experience
• Minimum 1–2 years of hands‑on GenAI project implementation experience
• Experience building production AI applications preferred

Good to Have

• Experience with enterprise AI governance and responsible AI
• Exposure to fine‑tuning and model optimization
• Open-source contributions or AI portfolio projects
• Experience in scalable distributed systems

What We Offer

• Opportunity to work on cutting‑edge enterprise AI solutions
• Exposure to Agentic AI and next‑generation AI architecturesFast‑paced innovation environment
• Career growth in one of the fastest‑growing technology domains