AI Architect

10Pearls, LLC; Karachi Division, Lahore, Islamabad; Sur place; PKR 3 000 000 - 6 000 000; Plein temps

Résumé du poste

10Pearls in Karachi seeks a hands-on AI Architect to design and deliver AI agents and automation across the Microsoft ecosystem. The role covers both pro-code and low-code options, including Azure AI Foundry, Copilot Studio, Microsoft 365 Copilot and Power Platform.

The architect will work directly with client stakeholders, lead technical discovery and contribute to the build within a small team. The ideal candidate has 8+ years in software engineering or solution architecture, with 2+ years

Qualifications

• 8+ years in software engineering or solution architecture.
• At least 2 years delivering generative AI solutions in production.
• Hands-on experience with Azure AI Foundry, including agents, model selection and evaluation.
• Hands-on or strong working experience with Copilot Studio and Power Automate.
• Good understanding of Microsoft 365, including Exchange, SharePoint, Teams, Graph and Entra ID.
• Working knowledge of Microsoft AI licensing, including Copilot, Copilot Studio capacity and Azure consumption.
• Experience with document extraction and analysis, including Azure Document Intelligence or similar tools.
• Practical experience with RAG, prompt design, agent orchestration and LLM evaluation.
• Understanding of AI security risks, including prompt injection and data leakage.
• Python skills sufficient to prototype and review code.
• Experience in client-facing consulting or services delivery.
• Able to work regular overlap hours with US Eastern time.

Responsabilités

• Define end-to-end architectures for AI agents, document processing and workflow automation.
• Recommend configure, build or buy options across Foundry, Copilot Studio, Microsoft 365 Copilot, Power Platform and third-party tools.
• Forecast license, capacity and token costs for each use case, including long documents.
• Design single and multi-agent solutions with clear roles, routing, tool use and human approval steps.
• Design extraction, parsing and analysis for long documents such as contracts, including OCR and chunking.
• Turn expert knowledge, policies and SOPs into structured content that agents can use reliably.
• Integrate with Outlook and shared mailboxes, SharePoint, Teams and Microsoft Graph.
• Assess and design access to line-of-business systems through APIs, data gateways or scheduled exports.
• Design for prompt injection defense, file and content safety, access control, audit logging and data residency.
• Set up evaluation datasets, regression suites, confidence thresholds and accuracy tracking.

Connaissances

Software engineering

Solution architecture

Generative AI

Python

Client-facing consulting

Outils

Azure AI Foundry

Copilot Studio

Power Automate

Microsoft 365

SharePoint

Teams

Microsoft Graph

Description du poste

About 10Pearls

10Pearls is a global, purpose-driven AI-Native digital engineering partner helping businesses re-imagine, digitalize, and accelerate. As an end-to-end digital technology partner, 10Pearls helps businesses create future-proof, transformative digital products that leverage emerging technologies. 10Pearls' clients include Global 2000 enterprises, high growth mid-size businesses, and some of the most exciting start-ups from industries like healthcare, fintech, energy, education, real estate, retail, and hi-tech. Headquartered in the Washington DC metro area, 10Pearls has product engineering and software development centers in North America, Latin America, Europe, and South Asia. To learn more, visit https://10pearls.com.

Role Overview

We are looking for a hands-on AI Architect to design and deliver AI agents and automation across the Microsoft ecosystem.

The role covers both pro-code and low-code options. This includes Azure AI Foundry, Copilot Studio, Microsoft 365 Copilot and Power Platform.

We expect the architect to choose the simplest option that meets the needs. Custom development should be used where it adds clear value.

The architect will work directly with client stakeholders, lead technical discovery and contribute to the build within a small team.

Responsibilities

• Solution architecture. Define end-to-end architectures for AI agents, document processing and workflow automation.

• Platform selection. Recommend configure, build or buy options across Foundry, Copilot Studio, Microsoft 365 Copilot, Power Platform and third-party tools.

• Cost modelling. Forecast license, capacity and token costs for each use case, including long documents.

• Agent design. Design single and multi-agent solutions with clear roles, routing, tool use and human approval steps.

• Document AI. Design extraction, parsing and analysis for long documents such as contracts, including OCR and chunking.

• Knowledge grounding. Work with the BA and SMEs to turn expert knowledge, policies and SOPs into structured content that agents can use reliably.

• Microsoft 365 integration. Integrate with Outlook and shared mailboxes, SharePoint, Teams and Microsoft Graph.

• Legacy integration. Assess and design access to line-of-business systems through APIs, data gateways or scheduled exports.

• AI security. Design for prompt injection defense, file and content safety, access control, audit logging and data residency.

• Evaluation and quality. Set up evaluation datasets, regression suites, confidence thresholds and accuracy tracking before and after go-live.

• Readiness and environments. Confirm licenses, permissions, access and environment ownership across development stages before build starts.

• Hands-on delivery. Contribute to prompts, agent configuration and code alongside the AI and integration engineers.

• Pipeline preparation. Assess upcoming use cases with the BA while current work is in build.

• Stakeholder communication. Explain trade-offs, cost and risk to business and technical stakeholders in plain language.

Requirements

• 8 or more years in software engineering or solution architecture, with at least 2 years delivering generative AI solutions in production.

• Hands-on experience with Azure AI Foundry, including agents, model selection and evaluation.

• Hands-on or strong working experience with Copilot Studio and Power Automate.

• Good understanding of Microsoft 365, including Exchange, SharePoint, Teams, Graph and Entra ID.

• Working knowledge of Microsoft AI licensing, including Copilot, Copilot Studio capacity and Azure consumption.

• Experience with document extraction and analysis, including Azure Document Intelligence or similar tools.

• Practical experience with RAG, prompt design, agent orchestration and LLM evaluation.

• Understanding of AI security risks, including prompt injection and data leakage.

• Python skills sufficient to prototype and review code.

• Experience in client-facing consulting or services delivery.

• Able to work regular overlap hours with US Eastern time.

Preferred qualifications

• Experience with contract review, legal tech or policy-based document checking.

• Experience with manufacturing, print, supply chain or fulfillment operations.

• Integration with ERP, MIS or other legacy operational systems.

• Experience with speech-to-text, video or knowledge capture tools for training content.

• Microsoft certifications such as Azure AI Engineer Associate or Azure Solutions Architect Expert.