Gen AI

Infosys; Hyderabad, Bengaluru, Mumbai; On-site; INR 1,500,000 - 2,200,000; Full time

Job summary

Infosys in Hyderabad is seeking a GenAI Engineer to design and implement scalable AI systems using Generative AI, agent frameworks, and MCP. The role emphasizes RAG pipelines, multi-agent orchestration, and enterprise integrations.

The ideal candidate brings 5–11 years of experience with hands-on GenAI development, strong Python skills, and familiarity with LLM APIs and prompt engineering. Immediate joiners preferred, Full-Time employment.

Qualifications

• Experience in GenAI-based application development with LLMs.
• Hands-on work with RAG pipelines and vector databases.
• Proficiency in Python and modern AI frameworks.

Responsibilities

• Design GenAI-powered applications using LLM ecosystems.
• Build and optimize RAG pipelines for context-aware AI.
• Develop agentic AI systems and multi-agent orchestration.
• Implement MCP for advanced prompt/context management.
• Integrate LLMs with enterprise APIs and databases.

Skills

Generative AI

RAG architectures

Agent Frameworks

Agentic AI systems

MCP Protocol

Python

LLM APIs

Prompt engineering

REST APIs

Tools

LangChain

AutoGen

CrewAI

FAISS

Pinecone

Weaviate

Azure OpenAI

Job description

Job Title: GenAI Engineer (511 Years) – Immediate Joiners Preferred

Experience: 5 – 11 Years

Employment Type: Full-Time

Job Summary

We are seeking an experienced GenAI Engineer with strong expertise in Generative AI, Agent Frameworks, Agentic AI, RAG (Retrieval-Augmented Generation), and MCP (Model Context Protocol). The ideal candidate will design and implement intelligent, scalable AI systems leveraging LLMs, multi-agent workflows, and contextual reasoning.

Candidates who can join immediately or within short notice periods are highly preferred.

Key Responsibilities

• Design and develop GenAI-powered applications using modern LLM ecosystems
• Build and optimize RAG pipelines for context-aware AI solutions
• Develop Agentic AI systems using frameworks like LangChain, AutoGen, CrewAI, or similar
• Implement and manage multi-agent orchestration and workflows
• Utilize Model Context Protocol (MCP) for advanced prompt and context management
• Integrate LLMs with enterprise systems, APIs, and databases
• Fine-tune prompts and evaluate model performance (accuracy, latency, cost)
• Ensure security, scalability, and reliability of AI solutions
• Collaborate with cross-functional teams including data engineering, product, and DevOps
• Stay updated on emerging GenAI tools, frameworks, and best practices

Required Skills & Qualifications

• Strong experience in Generative AI / LLM-based application development
• Hands-on experience with RAG architectures (vector DBs like FAISS, Pinecone, Weaviate, etc.)
• Expertise in Agent Frameworks (LangChain, AutoGen, CrewAI, etc.)
• Experience building Agentic AI systems / multi-agent orchestration
• Knowledge of MCP (Model Context Protocol) or equivalent context-management approaches
• Strong programming skills in Python
• Experience working with OpenAI, Azure OpenAI, or similar LLM APIs
• Familiarity with prompt engineering and evaluation techniques
• Experience with REST APIs, microservices architecture

Preferred Qualifications

• Experience with fine-tuning / embedding models
• Familiarity with vector databases and semantic search
• Exposure to cloud platforms (AWS / Azure / GCP)
• Knowledge of ML Ops / LLM Ops tools
• Experience with streaming pipelines and real-time AI systems
• Understanding of data privacy and AI governance