Staff AI Software Engineer

GE Vernova; Bengaluru; Hybrid; INR 4,000,000 - 7,000,000; Full time

Benefits offered by this job

Relocation assistance

Job summary

GE Vernova, Inc. in Bengaluru, India seeks a Staff AI Engineer to lead architecture, development, and end-to-end lifecycle of AI Agents and MCP servers. You will own the full stack from design to testing and production, ensuring scalable, secure, enterprise-ready workflows.

You will collaborate with internal teams and external contractors to drive technical reviews, integrations, and delivery using advanced AI capabilities, with emphasis on observability, prompts testing, and business impact.

Qualifications

• Bachelor’s degree in a technical field (CS, CE or equivalent).
• 6+ years of experience with at least one language (Python, Java, or Go).
• Proven track record shipping AI-enabled applications at scale.

Responsibilities

• Collaborate with cross-functional teams to build AI-native experiences.
• Build AI Agents, MCP Servers, Tools and integrate LLM capabilities.
• Implement RAG patterns for context-aware experiences.
• Drive end-to-end execution of medium-to-large features with independence.
• Mentor engineers; guide contractors and partners.

Skills

Python

Java

Go

JS/TS

Cloud platforms

Docker & Kubernetes

LLMs/AI services

Leadership

Code reviews

Testing & QA

Education

Bachelor’s degree

Tools

Strands

ADK

Bedrock AgentCore

LangChain

Job description

Job Description Summary

As a Staff AI Engineer, you will lead the architecture, development, and end-to-end lifecycle of our AI Agents and the underlying infrastructure that powers it. You will design and deploy AI agents and robust MCP (Model Context Protocol) servers that standardize data connectivity, skills, and tools. You will also own the full stack, from design and clean code implementation to rigorous testing and production support. By balancing high-level system strategy with hands-on technical execution, you will ensure our agentic workflows are scalable, secure, and seamlessly integrated into the enterprise ecosystem.

You will partner with internal teams and external contractors to lead technical reviews, integrations, and delivery execution. You will delivery using Coding Agents, establish testing approaches for prompts and model performance, and implement observability for AI features. We value autonomy, continuous learning, and clear business impact.

Job Description

Responsibilities:

• Collaborate with cross-functional teams (product, design, operations, infrastructure) to build AI-native application experiences
• Build AI Agents, MCP Servers, Tools and integrate LLM / generative AI capabilities into products, including structured prompting, memory management and context management.
• Implement retrieval-augmented generation (RAG) patterns (e.g., embeddings + retrieval) and contribute to context-aware and personalized user experiences
• Drive end-to-end execution of medium-to-large features with independence, contribute to technical direction within the team
• Mentor engineers; guide contractors and partners.

Required Qualifications:

• Bachelor’s degree in computer science, Computer Engineering, or related technical field
• 6+ years of experience using at least one general purpose programming language (Python [preferred], Java, or Go) and front-end experience with JavaScript/TypeScript
• Proven track record shipping production applications that incorporate LLMs, MCPs or AI services at scale
• Demonstrated experience leading technical teams and providing guidance to external contractors or vendors
• Strong experience with cloud platforms (AWS, GCP, or Azure) and advanced containerization (Docker, Kubernetes)
• Experience with technical oversight, code review processes, and quality assurance methodologies

Preferred Qualifications:

• Experience in Cloud Software Development, including architecture design, technical leadership, and system optimization
• Experience with Strands, ADK or Agent development frameworks.
• Experience with multiple LLM providers and advanced AI orchestration frameworks (e.g. Amazon Bedrock AgentCore, LangChain)
• Experience with modern front-end frameworks (React, Vue, or Angular) and advanced state management
• Experience with vector databases (e.g. pgvector) and embedding model optimization
• Experience with enterprise RAG architectures, semantic search optimization, and conversation memory management at scale
• Experience building and scaling AI-powered features for 100k+ users

Additional Information

Relocation Assistance Provided: Yes