A

Accenture

Advises businesses and runs their technology

AI / ML Engineer

AI Application EngineeringPosted on Nov 9
Full-timeMumbai, Maharashtra, IndiaNo salary listed

About the Job

Requirements

  • A minimum of 3 years of experience is required; an additional statement specifies a minimum of 5 years of experience with Large Language Models.
  • Proficiency with Large Language Models (LLMs).
  • Strong proficiency in Python and production-level software engineering practices, with hands-on experience building multi-agent systems using Google ADK (Agent Development Kit) or comparable agentic frameworks.
  • Hands-on experience deploying and customizing Gemini Enterprise and NotebookLM, and integrating with the Google Workspace ecosystem, including APIs, add-ons, and Drive/Docs connectors.
  • Experience managing agent session state, short-term context caching, and durable long-term memory backends, including vector databases and relational or NoSQL session stores.
  • Experience with MCP connectors to securely integrate third-party platforms, including iManage, NetDocuments, Relativity, DocuSign, Microsoft Office Suite, SharePoint, and JIRA, with Gemini Enterprise.
  • Understanding of authentication and authorization protocols, including IAM, OAuth 2.0, OIDC, service accounts, and Workload Identity Federation, across Google Cloud and third-party SaaS platforms such as Microsoft Entra ID, Salesforce, and Atlassian.
  • Working knowledge of enterprise access control lists, identity federation, permission trimming, and role-based access control across heterogeneous data sources.
  • Proficiency with Agent CLI and Antigravity for local simulation, debugging, prompt engineering, and execution graph tracing.
  • Experience configuring and maintaining automated CI/CD pipelines, including Cloud Build and GitHub Actions, for agent containerization, deployment, and test automation.
  • Practical knowledge of AI evaluation methodologies and trajectory analysis, and ability to perform root cause analysis on agent execution failures, tool errors, and prompt regressions.
  • 15 years of full-time education is required.

Responsibilities

  • Design, develop, and deploy production-grade multi-agent systems and agentic workflows using Gemini Enterprise.
  • Determine whether pro-code or no-code design is appropriate based on the customer's problem statement and data sources.
  • Design, deploy, and customize agents using the Agent Development Kit (ADK) and Agent Platform AI Reasoning Engine, and integrate them with Gemini Enterprise.
  • Build native integrations across Google Workspace applications, including Docs, Drive, Gmail, Calendar, and Meet, and NotebookLM for grounded enterprise research, document automation, and conversational discovery.
  • Architect scalable short-term session storage, conversation-state persistence, and long-term memory architectures for multi-agent interactions.
  • Implement end-to-end authentication and authorization perimeters for agents, Google Cloud services, and third-party SaaS integrations using IAM, OAuth 2.0, OIDC, and service identities.
  • Enforce fine-grained access control lists, user and group permission inheritance, and data governance policies so agents adhere to enterprise access boundaries.
  • Use Agent CLI and Antigravity for local prototyping, testing, emulation, distributed tracing, and root cause analysis.
  • Architect human-in-the-loop workflows, including interrupt and resume patterns between autonomous agents and human experts at critical decision points.
  • Build and maintain automated CI/CD pipelines, including Cloud Build, GitHub Actions, and GitLab CI, for versioned agent deployments, automated testing, and continuous regression evaluations.
  • Implement reasoning patterns such as Chain-of-Thought, ReAct, Plan-and-Solve, and Self-Reflection to enhance agent reliability.
  • Establish quantitative evaluation frameworks to measure agent trajectories, tool invocation precision and recall, and reasoning faithfulness.
  • Collaborate with client engineering and architecture teams to deploy, validate, and operationalize enterprise agentic AI solutions in client environments.

About the Company

Accenture

Advises businesses and runs their technology

Accenture advises large businesses and public agencies on strategy, builds their technology systems and runs ongoing operations. Its teams connect business planning with implementation, covering areas such as cloud migration, cybersecurity and customer experience. Consultants work with clients to redesign processes, while engineers integrate software from technology partners and maintain the resulting systems for multinational organizations. Clients pay for project work or continuing services, including application support and business processes such as finance and customer service. Accenture was founded in 1989 and has its headquarters in Dublin, Ireland.

Company size
10,001+
Company stage
IPO
Headquarters
Dublin, Ireland
Founded
1989

Recently Posted Jobs

Explore more opportunities at Accenture

See more jobs