15 days ago
Karachi, Pakistan +2 moreSenior
Responsibilities
- Define end-to-end architectures for AI agents, document processing, and workflow automation.
- Recommend configure, build, or buy options across Azure AI Foundry, Copilot Studio, Microsoft 365 Copilot, Power Platform, and third-party tools.
- Model license, capacity, and token costs for AI use cases, including long-document scenarios.
- Design single- and multi-agent systems with routing, tool use, human approval steps, and clear agent roles.
- Design document extraction, parsing, OCR, chunking, and analysis for long documents such as contracts.
- Convert expert knowledge, policies, and SOPs into structured content for reliable agent grounding.
- Integrate solutions with Outlook, shared mailboxes, SharePoint, Teams, Microsoft Graph, and legacy business systems.
- Design defenses against prompt injection, file and content risks, unauthorized access, audit gaps, and data residency issues.
- Establish evaluation datasets, regression suites, confidence thresholds, and accuracy tracking before and after launch.
- Confirm licenses, permissions, access, and environment ownership across development stages.
- Contribute prompts, agent configurations, and code alongside AI and integration engineers.
- Assess upcoming use cases with business analysts while current solutions are being built.
- Lead technical discovery and communicate trade-offs, cost, and risk to business and technical stakeholders.
Requirements
- At least 8 years of experience 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, Microsoft Graph, and Entra ID.
- Working knowledge of Microsoft AI licensing, 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.
- Ability to work regular overlap hours with US Eastern time.
- Preferred experience with contract review, legal technology, or policy-based document checking.
- Preferred experience with manufacturing, print, supply chain, or fulfillment operations.
- Preferred experience integrating ERP, MIS, or other legacy operational systems.
- Preferred 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 are preferred.
Benefits
- Regular overlap hours with US Eastern time are required; no other benefits or work arrangement details are stated.
About 10Pearls
10Pearls is a privately held digital engineering and AI consultancy that designs, builds, and modernizes software products for enterprises, mid-market companies, and startups. The company provides end-to-end services—product management, UX, cloud development, data/AI, cybersecurity, DevOps, and quality engineering—with global delivery centers across North America, Latin America, the UK, and South Asia. Headquartered in Vienna, Virginia, its clients have included brands such as AARP, Capital One, PayPal, Adobe, and National Geographic.