Lead Generative AI Developer

EPAM Systems; Coimbatore District; On-site; INR 4,000,000 - 6,000,000; Full time

Job summary

EPAM Systems in India seeks a Lead Generative AI Developer with AWS to design and build GenAI solutions using Bedrock and similar platforms, integrating foundation models with enterprise systems and ensuring secure, responsible AI practices across business scenarios.

You will develop AI-powered applications, orchestrate prompt engineering, RAG architectures, and deploy chatbots, knowledge assistants and document processing solutions, collaborating with cross-functional teams.

Qualifications

• Bachelor’s or master’s degree in Computer Science, Engineering or related field.
• 10+ years of overall IT experience and 5+ years in cloud architecture.
• Hands-on experience with AWS cloud services such as EC2, S3 and Lambda, as well as RDS, VPC and IAM.

Responsibilities

• Design and build GenAI solutions using Amazon Bedrock or similar GenAI platforms.
• Integrate foundation models with enterprise applications and APIs.
• Perform prompt engineering and optimization.
• Develop RAG architectures.
• Create AI-powered applications such as chatbots, copilots, knowledge assistants and document processing solutions.
• Evaluate and fine-tune LLM-based use cases for business scenarios.
• Ensure data privacy, model governance and responsible AI practices.

Skills

GenAI

AWS

Bedrock

Cloud architecture

Python

React/Node.js

LLMs

Prompt engineering

RAG

Education

Bachelor’s or Master’s in CS/Engineering

Tools

Amazon Bedrock

EC2

S3

Lambda

RDS

VPC

IAM

Job description

We are looking for a Lead Generative AI Developer with AWS to design and build cutting-edge GenAI solutions using Amazon Bedrock and similar platforms. In this role, you will develop AI-powered applications, integrate foundation models with enterprise systems and ensure secure, responsible AI practices across business scenarios.

Responsibilities

• Design and build GenAI solutions using Amazon Bedrock or similar GenAI platforms
• Integration with foundation models such as Anthropic Claude and Titan
• Perform prompt engineering and optimization
• Develop RAG (Retrieval Augmented Generation) architectures
• Create AI-powered applications such as chatbots, copilots, knowledge assistants and document processing solutions
• Evaluate and fine-tune LLM-based use cases for business scenarios
• Integrate GenAI models with enterprise applications and APIs
• Implement secure AI architectures aligned with enterprise and regulatory standards
• Ensure data privacy, model governance and responsible AI practices

Requirements

• Bachelor's or master's degree in Computer Science, Engineering or related field
• 10+ years of overall experience in IT and 5+ years in cloud architecture
• Hands-on experience with AWS cloud services such as EC2, S3 and Lambda, as well as RDS, VPC and IAM
• Proven experience with Amazon Bedrock or similar GenAI platforms
• Expertise in LLMs, prompt engineering and embeddings alongside RAG frameworks
• Knowledge of programming languages such as Python, React or Node.js
• Proficiency in designing API-driven and microservices architectures

Nice to have

• Familiarity with LangChain, LlamaIndex or similar frameworks
• Knowledge of vector databases such as OpenSearch, Pinecone or FAISS
• Understanding of MLOps and model lifecycle management
• Exposure to multi-cloud environments such as Azure or OpenAI