Gen AI Engineer

Coforge; Hyderabad, Pune District, Greater Noida; On-site; INR 400,000 - 680,000; Full time

Job summary

Coforge in Hyderabad, India is seeking a GenAI Engineer to lead design, development, and delivery of enterprise-grade Generative AI and Agentic AI solutions. You will guide architecture, mentor teams, and drive production-ready deployments.

The role emphasizes prompt engineering, evaluation, guardrails, observability, and collaboration with product owners and stakeholders to translate business needs into scalable AI applications.

Qualifications

• Strong hands-on experience with Python-based GenAI stacks and related frameworks.
• Experience with Azure AI Foundry, OpenAI, AWS Bedrock or similar platforms.
• Strong understanding of LLMs, RAG, Vector Databases, AI Agents, Prompt Engineering, LLM Evaluation, and AI Observability.
• Experience with CI/CD, MLOps, containerization, and cloud-native deployments.
• Strong stakeholder communication and leadership abilities.

Responsibilities

• Lead end-to-end delivery of GenAI and Agentic AI solutions.
• Design and implement RAG, AI Agents, MCP, multi-agent orchestration, and LLM-based applications.
• Guide teams in prompt engineering, evaluation frameworks, guardrails, observability, and performance optimization.
• Translate business requirements into scalable AI solutions.
• Establish coding standards, architecture patterns, and engineering best practices.
• Conduct technical reviews and mentor GenAI engineers.
• Collaborate with architects, product owners, and business stakeholders.
• Drive production readiness, monitoring, security, and Responsible AI compliance.

Skills

LLMs

RAG

Vector Databases

AI Agents

Prompt Engineering

LLM Evaluation

AI Observability

Strong stakeholder communication

Leadership abilities

Tools

Python

FastAPI

LangChain

LangGraph

Semantic Kernel

AutoGen

MCP

Azure AI Foundry

OpenAI

AWS Bedrock

CI/CD

MLOps

containerization

cloud-native deployments

Job description

GenAI Engineer-

Role Purpose

Lead the design, development, and delivery of enterprise-grade Generative AI and Agentic AI solutions. Drive technical execution, mentor engineering teams, and ensure scalable, secure, and production-ready AI deployments.

Key Responsibilities

• Lead end-to-end delivery of GenAI and Agentic AI solutions.
• Design and implement RAG, AI Agents, MCP, multi-agent orchestration, and LLM-based applications.
• Guide teams in prompt engineering, evaluation frameworks, guardrails, observability, and performance optimization.
• Translate business requirements into scalable AI solutions.
• Establish coding standards, architecture patterns, and engineering best practices.
• Conduct technical reviews and mentor GenAI engineers.
• Collaborate with architects, product owners, and business stakeholders.
• Drive production readiness, monitoring, security, and Responsible AI compliance.

Required Skills

• Strong hands-on experience with Python, FastAPI, LangChain, LangGraph, Semantic Kernel, AutoGen, MCP.
• Experience with Azure AI Foundry, OpenAI, AWS Bedrock or similar platforms.
• Strong understanding of:
• LLMs
• RAG
• Vector Databases
• AI Agents
• Prompt Engineering
• LLM Evaluation
• AI Observability
• Experience with CI/CD, MLOps, containerization, and cloud-native deployments.
• Strong stakeholder communication and leadership abilities.