Responsibilities
- Build multi-agent orchestration systems using Vertex AI, Agent Builder, LangGraph, and AutoGen.
- Design scalable and resilient pipelines for LLM reasoning, tool calling, memory management, and human-in-the-loop flows.
- Lead the design and implementation of RAG systems using Vertex AI Search, Matching Engine, and enterprise vector stores.
- Define and enforce security-first GCP infrastructure standards across GKE, Cloud Run, Eventarc, and Apigee.
- Drive MLOps practices including model evaluation, agent observability, tracing, logging, and continuous improvement loops.
- Partner with product, data science, and platform teams to translate business requirements into agentic solutions.
- Conduct code reviews and architecture reviews.
- Mentor developers with three to five years of experience.
- Contribute to internal developer platforms, SDKs, and reusable agent components.
- Own delivery of highly available and low-latency services, including SLO and SLA ownership.
Requirements
- At least 7.5 years of experience is required; the role also describes a five-to-eight-year software or platform engineering experience range.
- At least two years of experience focused on AI, ML, or agentic systems.
- Deep expertise in GCP services including Vertex AI, Gemini, Vertex AI Pipelines, Feature Store, GKE, and Pub/Sub.
- Proven experience building production-grade LLM-powered applications with tool use, multi-turn reasoning, and agent memory.
- Proficiency in Python.
- Strong understanding of asynchronous patterns, concurrency, and distributed systems.
- Hands-on experience with agentic frameworks such as ADK, LangChain, LangGraph, and CrewAI.
- Experience with vector databases, embedding pipelines, and hybrid search architectures.
- Strong command of GCP security, including IAM, Workload Identity, VPC Service Controls, and Secret Manager.
- Track record of delivering highly available and low-latency services with SLO and SLA ownership.
- Completion of 15 years of full-time education.
Benefits
- Remote or hybrid work mode.
- Full-time employment.
Tech Stack
Categories
About Accenture
Accenture helps the world’s leading enterprises reinvent by building their digital core and unleashing the power of AI to create value at speed for organizations across industries. Our strategy is to be the reinvention partner of choice for our clients and lead in the safe, widespread adoption of AI, and to be the most client-focused, AI-enabled, great place to work in the world. We bring together the talent of our approximately 786,000 people with proprietary assets and platforms, deep process and industry expertise, and leading ecosystem relationships to deliver end-to-end solutions and measurable outcomes at scale. Through our Reinvention Services, we offer broad expertise across Cybersecurity, Digital Core, Finance, Industry and Enterprise, Song, Supply Chain and Engineering, and Talent, with advanced capabilities in AI and Data, Industry and Process, and Technology. We serve approximately 9,000 clients and generated approximately $70 billion in FY25 revenue. Visit us at accenture.com. This LinkedIn company page is moderated. When engaging with Accenture, we encourage everyone to: - Use common courtesy and be respectful of others. - Create your own original content and avoid content that you know to be fraudulent. - Never repost someone else's copyrighted work, unless you have permission. - Never post personal, identifying, or confidential information. We reserve the right to delete comments or posts we deem to be: - Profane, obscene, inappropriate, offensive, abusive material. - Spam, repeated comments and commercial messages and personal advertisements. - Discriminatory or that contain hateful speech of any kind regarding age, gender, race, religion, nationality, sexual orientation, gender identity or disability. - Threats; personal attacks; abusive, defamatory, derogatory, or inflammatory language; or stalking or harassment of any individual, entity or organization. - False, inaccurate, libelous, or otherwise misleading in any way.