Principal Architect, Agentic AI for Application Maintenance Services

We are looking for a Principal Architect for Agentic AI in Application Maintenance Services to join our growing team and lead the design and implementation of secure, reliable AI agents for application support and operations.

Mail us at: [email protected]

• United States (Remote)
• Remote – open to US-based candidates only

Why Join Us

About Saarthee

-------------------

Saarthee is a Global Strategy, Analytics, Technology and AI consulting company, where our passion for helping others fuels our approach and our products and solutions. Our diverse and global team work with one objective in mind: Our Customers’ Success. At Saarthee, we are passionate about guiding organizations towards insights fueled success. That’s why we call ourselves Saarthee–inspired by the Sanskrit word ‘Saarthi’, which means charioteer, trusted guide, or companion. Cofounded in 2015 by Mrinal Prasad and Shikha Miglani, Saarthee already encompasses all the components of Data Analytics consulting. Saarthee is based out of Philadelphia, USA with office in UK and India.

Position Summary

--------------------

Location

: United States (Remote)

Work Mode

: Remote – open to US-based candidates only

Min-Max Experience

: 12+ Years

Work Authorization

: Must be authorized to work in the US without current or future visa sponsorship

As a Principal Architect for Agentic AI in Application Maintenance Services (AMS), you will lead the architecture and implementation of enterprise AI for application support and operations, including routing, triage, resolution, remediation, root-cause analysis (RCA), and knowledge agents.

This role combines AI and platform architecture with a deep understanding of ITSM and SRE to move AMS from AI-assisted lookup to controlled, closed-loop, agent-enabled operations. We are looking for an architect with experience across large-scale production environments who can lead architects, AI engineers, and application teams.

Your Role Responsibilities and Duties

-----------------------------------------

• AMS Agent & Platform Architecture: Define the roadmap for routing, triage, resolution, remediation, RCA, and knowledge agents across the full lifecycle, from detection through learning.
• Enterprise Knowledge & RAG: Architect a governed knowledge base of runbooks, incidents, RCA records, logs, and telemetry, with permission-aware retrieval.
• MCP & Enterprise Integration: Define Model Context Protocol (MCP) tool contracts for ticketing, observability, and change workflows, with action tiers ranging from read-only to approval-required.
• Security & Operational Risk: Set least-privilege, data-masking, and prompt-injection controls, and classify agent risk by criticality, action type, and reversibility.
• Evaluation, Reliability & AgentOps: Build golden datasets from historical incidents, and define observability and staged rollout from sandbox to controlled execution.
• Operating Model & Adoption: Define cross-team responsibilities and tie adoption to MTTR, ticket avoidance, and repeat-incident reduction.

Required Skills and Qualifications

--------------------------------------

• 12+ years of experience in application support, SRE, solution architecture, or operations transformation.
• Demonstrated architecture experience across large-scale production environments.
• Experience with incident, problem, change, service-request, and knowledge-management processes.
• Experience leading architects, AI engineers, and application teams.
• Strong architecture experience in application support, SRE, ITSM, or enterprise integration.
• Understanding of LLMs, RAG, embeddings, tool calling, and agent workflows.
• Knowledge of hybrid retrieval, vector search, and knowledge graphs.
• Experience with APIs, identity, security, cloud, and observability platforms.
• Experience integrating JIRA, ServiceNow, GitHub/GitLab, and monitoring tools.

Preferred Qualifications

----------------------------

• Degree in Computer Science, Engineering, or Information Systems.
• Experience with Claude, Gemini, GPT, LangGraph, or ADK.
• Knowledge of New Relic, OpenSearch, or Elastic.
• ITIL, SRE, cloud, or AI certification; telecom or regulated-industry experience.

Mandatory Skills

--------------------

ITSM & SRE, Solution Architecture, LLMs & RAG, Agent Workflows, ServiceNow / JIRA Integration, Observability Platforms.

What We Offer

-----------------

• Bootstrapped and financially stable with high pre-money valuation.
• Above-industry remuneration.
• Additional compensation tied to renewals and pilot project execution.
• Additional lucrative business development compensation.
• Chance to work closely with industry experts driving strategy with data and analytics.
• Firm-building opportunities that provide a platform for holistic professional development, growth, and branding.
• An empathetic, excellence-driven, and results-focused organization that believes in mentoring and growing a team with a constant emphasis on learning.