Job Title

Job Title: STRIDE AI Engineer / Architect Location: Remote(25% Travel is required)For Canada location will be Toronto, ONFor USA location will be Princeton, NJRole Overview We are looking for an AI Engineer / Architect to design, build, and evolve an enterprise-grade AI platform that accelerates root cause analysis, secure automation, code intelligence, and quality engineering.This role blends AI engineering, software architecture, security-by-design (STRIDE), and platform thinking.You will work at the intersection of Generative AI, secure software development, auditability, and large-scale engineering systems. Key Responsibilities AI Platform & Architecture Design and evolve the AI platform architecture across RCA, code intelligence, QA automation, and monitoring. Apply threat modeling and secure-by-design principles to all AI workflows. Define reference architectures for: AI-assisted RCA Knowledge graphs & embeddings PR automation with human-in-the-loop AI-driven QA (Playwright + Claude/GPT) AI Engineering & Automation Build AI pipelines using LLMs (Claude, GPT) for: Root cause analysis Code understanding and fix suggestions Test case generation Implement retrieval-augmented generation (RAG) and knowledge graph-based reasoning. Design prompt frameworks with guardrails, explainability, and audit logs. Code Intelligence & LLMOps Integration (Must have) Hands-on Coding (Mandatory): Strong, recent hands-on experience building production systems using Python (primary) and one of TypeScript/JavaScript, Java, or C#. This role codes regularly and owns delivered systems. Code Intelligence Systems: Proven experience building or integrating AST-based code analysis, dependency graphs, knowledge graphs, embeddings, and RAG pipelines for large, multi-repo codebases. Production LLMOps Ownership: Operated LLMs in production (Claude/GPT) with ownership of prompt versioning, evaluation, guardrails, cost controls, retries, fallbacks, and latency optimization. LLMOps CI/CD & Observability: Implemented CI/CD for prompts and models, automated regression tests for LLM outputs, telemetry (cost, quality, latency), tracing, and rollback strategies. Security & Platform Integration: Hands-on implementation of STRIDE-based security, RBAC, audit logging, data isolation, and integration with Git, CI/CD pipelines, cloud infrastructure, and DevOps tooling. Technical Leadership Act as a Principal Engineer / Enterprise Architect mindset within the team. Mentor engineers on: Secure AI development System design Responsible AI usage Influence platform standards and long-term technical strategy. Required Qualifications Core Skills 8+ years in software engineering, platform engineering, or architecture roles Strong experience with: Distributed systems Cloud platforms (Azure / AWS / GCP) API-driven architectures Hands-on experience with: LLMs (Claude, GPT, or equivalent) RAG pipelines, embeddings, vector databases Prompt engineering Security & Governance Solid understanding of: STRIDE threat modeling Secure SDLC Identity & access management Experience building systems that are auditable and compliant by design DevOps & QA Experience with: CI/CD pipelines Git-based workflows Automated testing frameworks (Playwright preferred) Familiarity with: Test automation strategies Quality metrics and coverage Preferred Qualifications Experience in regulated environments (finance, audit, healthcare) Knowledge of: Knowledge graphs Static & dynamic code analysis Observability (logs, metrics, traces) Prior experience in platform modernization or developer productivity tools What Success Looks Like AI platform is trusted by engineers, QA, security, and leadership Measurable reduction in: MTTR Defect leakage Manual effort AI automation operates with full governance and explainability Platform scales across teams safely Why Join Work on cutting-edge, responsible AI Build a flagship internal AI platform Influence enterprise-wide engineering practices Operate at the intersection of AI, security, audit, and architecture