Job Title

This role can be based in US or Canada - EST working hoursRole & Responsibilities Overview:Architecture & Technical LeadershipDefine end-to-end architecture for agentic AI-enabled platform across data, AI, orchestration, and integration layersDesign and govern agentic orchestration framework for multi-step workflowsEstablish architecture patterns for - RAG and grounding, Vector search and retrieval, MCP tool access layer, prompt management and evaluationPlatform & Integration DesignDefine integration architecture across - Lakehouse, ODS, document systems; Underwriting systems and third-party APIsDesign configurable, metadata-driven framework for multi-LOB onboardingDefine API/microservices patterns (Python/.NET hybrid)AI & GenAI EnablementDefine where and how to use - GenAI vs deterministic logic, agentic workflows vs pipeline workflowsEstablish multimodal integration approach combining structured, unstructured, and external dataDesign prompt lifecycle, evaluation, and optimization strategyGovernance, Safety & ModelOpsDefine AI safety and guardrails (PII, hallucination control, policy constraints)Establish ModelOps and PromptOps frameworksEnsure explainability, auditability, and traceability of AI outputsProgram LeadershipLead technical execution across AI, data, and platform teamsGuide engineers (AI, data, full-stack) and ensure alignment with architectureDrive technical decisions and stakeholder communicationCandidate Profile:Experience: 1015+ years in software/data/AI engineering with 46+ years in AI/ML/GenAI architectureBackground: Strong experience in designing enterprise-scale platforms and distributed systemsDomain (good to have): Insurance / reinsurance / financial servicesEducation: Bachelor's or Master's in Computer Science, Engineering, Data Science, or related fieldProfile Type: Hands-on architect with ability to balance strategy + executionTechnical skills:GenAI & Agentic Frameworks - Semantic Kernel/ LangGraph (or similar orchestration frameworks); LLM integration (Azure OpenAI, OpenAI APIs, etc.); Prompt engineering, prompt lifecycle designRetrieval & RAG - Azure AI Search (indexing, vector search, hybrid search); Embedding pipelines and retrieval optimization; RAG design, grounding strategies, context managementTool Access & Integration - MCP (Model Context Protocol) architecture and tool design; API design (FastAPI / REST / microservices); Integration with enterprise systems and third-party APIsAI Safety & Governance - NVIDIA NeMo Guardrails;Microsoft Presidio (PII detection/masking); Guardrails for prompt injection, hallucination controlEvaluation & ModelOps - Azure AI Foundry (model hosting, versioning, monitoring); Evaluation frameworks (LLM-as-judge, test datasets); Prompt/version control, cost/latency monitoringDevOps & Observability - CI/CD pipelines (Azure DevOps / GitHub Actions); Logging, monitoring, observability (App Insights, etc.); Performance tuning and scalability