Immediate Req : AI Engineer | Bangalore | Immediate Joiner

EY; Bengaluru; Hybrid; INR 1,800,000 - 4,000,000; Full time

Job summary

EY in Bengaluru is seeking an AI Engineer to build production-grade agentic AI systems for enterprise use. You will develop multi-agent workflows, integrate LLMs into existing enterprise apps, and ensure reliable, secure deployments in production.

You will work hands-on on agents, orchestration, and supporting infra, collaborating with platform, security, and product teams to deliver scalable solutions using LangGraph, LangChain, and modern cloud AI platforms.

Qualifications

• 4–9 years in ML/AI with production systems.
• At least 1 year building custom agentic AI apps.
• Strong Python skills and modern development practices.
• Hands-on with LLMs and prompt engineering across the lifecycle.
• Experience building AI agents with LangGraph.
• Familiar with one enterprise cloud AI platform (Azure/AWS/Google) deployment.

Responsibilities

• Build AI agents and multi-agent systems using LangGraph and LangChain.
• Develop and tune prompt workflows across GPT, Claude, LLaMA.
• Create REST APIs, WebSocket services, and event-driven pipelines.
• Automate testing and releases with Jenkins CI/CD; use Git/Jira/Confluence.
• Deploy AI applications in enterprise with best practices.
• Coordinate with platform, security, and product teams for scalable deployments.

Skills

Machine Learning

Agentic AI

Python

LangGraph

LangChain

LLMs

REST APIs

WebSockets

CI/CD

Git

Communication

Cross-functional teamwork

Tools

LangGraph

LangChain

Jenkins CI/CD

Git

REST APIs

WebSocket

Azure AI Foundry

AWS Bedrock

Google Gemini Enterprise

Databricks

Job description

AI Engineer- We are seeking a AI Engineer to build and deliver production-grade agentic AI systems for enterprise use. The engineer will develop multi-agent workflows, integrate large language models into existing enterprise systems, and support the deployment and automation needed to run them reliably and securely in production. This is a hands-on engineering engagement. The work centers on building agents, orchestration logic, and supporting infrastructure that performs under real production workloads, not on proof-of-concept or advisory work.

Scope of Work :

• Build AI agents and multi-agent systems using frameworks with LangGraph and LangChain tools.
• Develop and tune prompt engineering workflows across multiple LLMs (GPT, Claude, LLaMA), balancing reliability, cost, and latency.
• Develop REST APIs, WebSocket services, and event-driven pipelines for real-time AI services that remain stable under load.
• Automate testing and releases through Jenkins CI/CD, and maintain code and documentation standards using Git, Jira, and Confluence.
• Deployment of AI Application in enterprise adhering to best practices
• Use AI-augmented development tools such as Claude Code and Codex to accelerate delivery.
• Coordinate with platform, security, and product teams to deliver scalable, secure deployments.

Must-Have Skills :

• 4-9 years in Machine Learning, AI, or a related field, with production systems delivered.
• At least 1 year building custom Agentic AI applications
• Strong Python skills and sound modern development practices.
• Hands-on experience with LLMs and prompt engineering across the full application lifecycle.
• Demonstrated experience building AI agents with LangGraph.
• Familiarity with at least one enterprise cloud AI platform for building and deploying agentic applications, such as Azure AI Foundry, AWS Bedrock, or Google Gemini Enterprise, including cloud-native deployment practices.
• Working knowledge of REST APIs, WebSockets, and event-driven systems.
• Proficiency with CI/CD tooling (Jenkins) and version control (Git).
• Fluency with AI-augmented development tools for rapid prototyping.
• Strong written and verbal communication, an analytical approach to problem-solving, and the ability to work independently within a cross-functional team.
• Data layer curations and integration with source system for agentic application

Good-to-Have Skills :

• Familiarity with Databricks.
• Exposure to MLOps/LLMOps workflows and application monitoring.
• Knowledge of enterprise security, compliance, and governance for AI systems.
• Familiarity with code and model lifecycle management practices.

Note : Immediate joiners are preferred.

Thanks.

Regards,

Tanvi Shinganwade | HR Associate | Talent Team

Website: http://www.ey.com