Project Role : AI Infrastructure Architect

Project Role Description : Architect and build custom Artificial Intelligence (AI) infrastructure/hardware solutions. Optimize AI infrastructure/hardware performance, power consumption, cost and scalability of computational stack. Advise on AI infrastructure technology and vendor evaluation, selection and full stack integration.

Must have skills : AI Agents &

- Workflow Integration

Good to have skills : NA

Minimum 7.5 year(s) of experience is required

Educational Qualification : 15 years full time education

Summary

The Agentic Manager is responsible for end-to-end design, development, and operationalization of Agentic AI solutions for Infrastructure Managed Services. This role requires deep hands-on expertise across agentic frameworks, automation, AI integration, and infrastructure domains (Data Center, Cloud, Network, Compute, Storage etc). Collaboration with various teams to align infrastructure capabilities with project goals is a key aspect of daily activities.

Roles &

Responsibilities

-Agentic AI Engineering (Primary Accountability)

-Design and implement agentic AI solutions addressing infrastructure operations use cases

-Build single-agent and multi-agent systems using planner–executor, tool-using, and reflection patterns.

-Develop reusable agent frameworks, tools, and workflows aligned with enterprise standards.

-Infrastructure Domain Ownership

-Posses strong Infrastructure Managed Services expertise

-Act as a technical domain specialist for infra-focused agentic solutions.

-Platform &

- Tool Integration

-Integrate agents with enterprise platforms including:

-ITSM tools (ServiceNow – Incident, Change, CMDB)





-Monitoring & observability tools (SCOM, Dynatrace, AppDynamics, Prometheus, Grafana)

-Automation platforms (Rundeck, Ansible, Terraform)

-Develop secure Python-based tools and APIs that agents can reliably invoke.

-LLM &

- Agent Framework Implementation

-Work hands-on with LLMs in a model-provider-agnostic manner.

-Implement agent capabilities using frameworks such as LangChain / LangGraph, AutoGen / CrewAI (or similar)

-Manage Memory and context optimization, and cost, latency, and reliability trade-offs

-Security, Governance &

- Reliability

-Ensure agent solutions comply with Enterprise security standards

-Implement Human-in-the-loop controls, Guardrails and Failure handling and rollback mechanisms

-Delivery &

- Stakeholder Collaboration

-Independently own delivery of assigned agentic use cases.

-Collaborate with Infrastructure SMEs, Platform and automation teams, and Architecture and governance teams

-Produce clear technical documentation.

Professional &

- Technical Skills:
- Must Have Skills: Proficiency in AI Agents &
- Workflow Integration.
- Python (advanced) – automation, APIs, async workflows

-REST APIs, authentication mechanisms, JSON

-Strong knowledge of Data Center and Cloud administration, as well as Monitoring, Observability and ITSM platforms.

-Experience building agent-based systems (beyond chatbots)

-Solid understanding of Context and memory management

-Experience with AIOps or auto-remediation platforms

-Exposure to MCP

Additional Information

- The candidate should have minimum 7.5 years of experience in AI Agents &
- Workflow Integration.
- This position is based at our Pune/Bengaluru office.
- A 15 years full time education is required.

📌 AI Agents & Workflow Integration (Pune)
🏢 Accenture
📍 Pune