LLM Full Stack Engineer
Project Role Description : Develop and integrate applications with Large Language Models (LLMs) and other enterprise services. Leverage front-end and server-side technologies to develop APIs, implement DevOps practices, and optimize Artificial Intelligence (AI) applications.
Must have skills : Large Language Models (LLMs)
Good to have skills : NA
Minimum 7.5 year(s) of experience is required
Educational Qualification : 6 to 10 years of overall experience including 3 years in Python backend cloud integration or platform engineering
Summary:
We are seeking a Senior Gemini Enterprise Engineer to build, integrate, deploy, and operate enterprise AI solutions using Gemini Enterprise, Google Cloud, Vertex AI, enterprise search, and agent platforms. The role will deliver secure, scalable, and production-ready enterprise search, knowledge assistants, copilots, and AI agents that respect user permissions and meet agreed quality, reliability, performance, and cost targets.
Roles & Responsibilities:
AI Solution Development
Configure and develop Gemini Enterprise applications, data stores, connectors, and custom ingestion services validate metadata, refresh, deletion, and access-control behavior.
Build Python services, Gemini and Vertex AI integrations, and agents using Google Agent Development Kit (ADK) or an appropriate framework, including prompts, structured outputs, tool calls, workflow state, approvals, and human-in-the-loop controls.
Translate solution designs and business requirements into maintainable, scalable, and testable technical implementations.
Enterprise Search, RAG & Agents
Build and tune RAG pipelines covering document parsing, chunking, embeddings, semantic and hybrid retrieval, reranking, grounding, and source attribution.
Diagnose and resolve missing, stale, unauthorized, or poorly ranked evidence and improve retrieval and answer quality.
Develop and deploy custom and multi-agent workflows, tool integrations, and enterprise automation using supported Gemini Enterprise integration patterns.
Integration, Security & Governance
Integrate enterprise APIs, databases, SaaS products, and line-of-business applications using secure and resilient patterns, including authentication, scoped permissions, validation, retries, timeouts, and duplicate-action prevention.
Implement IAM, service identities, OAuth, secrets management, source-level permissions, least-privilege access, and secure environment separation.
Apply Responsible AI, security, privacy, auditability, and governance controls, including protection against prompt injection, data leakage, unauthorized retrieval, and unsafe actions.
Evaluation, DevOps & Production Support
Create automated and human evaluation approaches for grounding, relevance, safety, hallucination management, agent effectiveness, and task completion.
Implement automated quality, security, and regression tests maintain CI/CD, infrastructure as code, configuration and prompt versioning, and release controls.
Instrument logging, tracing, monitoring, latency, consumption, and cost troubleshoot failures, optimize production performance, and support releases and incidents.
Engineering Leadership
Conduct design and code reviews, mentor engineers, and promote maintainable engineering standards across Python services, APIs, retrieval pipelines, agents, and cloud-native components.
Create reusable patterns, accelerators, templates, operational documentation, and reference implementations while ensuring alignment with approved architecture.
Professional & Technical Skills:
Google Cloud and Enterprise AI
Hands-on Google Cloud delivery experience, including Gemini or Vertex AI APIs and suitable application hosting such as Cloud Run or an agent runtime.
Practical experience configuring or developing enterprise AI, search, knowledge-assistant, copilot, or agent solutions.
Software, Search and Agent Engineering
Strong Python and API development skills, with working knowledge of SQL, JSON, Git, automated testing, error handling, and maintainable service design.
Practical RAG or enterprise-search implementation experience and understanding of document processing, embeddings, retrieval quality, grounding, structured outputs, and prompt engineering.
Experience with tool-using LLM applications, agent orchestration, workflow state, function calling, and enterprise-system integrations.
Security, DevOps and Operations
Working knowledge of IAM, SSO, OAuth, service identities, secrets, source-level permissions, and testing of unauthorized access scenarios.
Experience with containers, CI/CD, infrastructure as code, logging, tracing, monitoring, and supporting a deployed service beyond a demonstration.
Understanding of LLMOps practices, including evaluation pipelines, prompt and configuration management, regression testing, release governance, and production monitoring.
Collaboration and Technical Leadership
Strong problem-solving, troubleshooting, communication, and collaboration skills, with the ability to work effectively with architects, product teams, security teams, and business stakeholders.
Experience mentoring engineers, reviewing technical deliverables, and working in agile and geographically distributed delivery teams.
Preferred Experience
Direct Gemini Enterprise or Google Agentspace configuration and implementation experience.
Google ADK, production agent runtimes, Vertex AI Search or Discovery Engine APIs, and MCP or A2A integrations.
LangGraph, LangChain, multi-agent orchestration, enterprise knowledge management, taxonomy, ontology, or knowledge-graph solutions.
GenAI evaluation, observability, safety, governance, or Responsible AI frameworks.
Relevant Google Cloud, GenAI, or AI engineering certification.
Additional Information:
- The candidate should have minimum 7.5 years of experience in Large Language Models (LLMs).
- This position is based at our Bengaluru office.
- 6 to 10 years of overall experience including 3 years in Python backend cloud integration or platform engineering is required.
Bengaluru
Equal Employment Opportunity Statement
All employment decisions shall be made without regard to age, race, creed, color, religion, sex, national origin, ancestry, disability status, veteran status, sexual orientation, gender identity or expression, genetic information, marital status, citizenship status or any other basis as protected by federal, state, or local law.
Please read Accenture’s Recruiting and Hiring Statement for more information on how we process your data during the Recruiting and Hiring process.
We work with one shared purpose: to deliver on the promise of technology and human ingenuity. Every day, more than 775,000 of us help our stakeholders continuously reinvent. Together, we drive positive change and deliver value to our clients, partners, shareholders, communities, and each other.
We believe that delivering value requires innovation, and innovation thrives in an inclusive and diverse environment. We actively foster a workplace free from bias, where everyone feels a sense of belonging and is respected and empowered to do their best work.
At Accenture, we see well-being holistically, supporting our people’s physical, mental, and financial health. We also provide opportunities to keep skills relevant through certifications, learning, and diverse work experiences. We’re proud to be consistently recognized as one of the World’s Best Workplaces™.
Join Accenture to work at the heart of change. Visit us at www.accenture.com.
We have been alerted to the existence of fraudulent messages asking job seekers to set up payment to cover various costs associated with establishing employment at Accenture. No one is ever required to pay for employment at Accenture. If you are contacted by someone asking for payment, please do not respond, and contact us at india.fc.check@accenture.com immediately.