Responsibilities:
- Design, build, deploy, and maintain production LLM‑based solutions and agent workflows.
- Own the technical strategy and reference architecture for enterprise AI solutions across multiple teams and business functions.
- Lead high-complexity, cross-functional AI initiatives from ambiguous problem definition through production adoption and measurable business outcomes.
- Define and evolve reusable platform capabilities, implementation standards, and governance patterns that enable safe, scalable AI adoption beyond a single team.
- Review citizen developer AI agents / solutions to provide recommendations for optimization, ensure compliance with guidelines and measure value.
- Influence roadmap and investment decisions across the company through technical leadership and business-value analysis.
- Drive technical debates, align stakeholders on tradeoffs, and unblock multi-team execution for strategically important AI initiatives.
- Implement, review, and validate code produced by models; write production‑quality code and run code reviews to ensure correctness and security.
- Build robust integrations and connectors (MCP, REST/GraphQL APIs, webhooks, SDKs, CLIs) between AI tooling and enterprise SaaS (e.g., Okta, Google Workspace, Slack, Jira, Confluence, Jamf).
- Own end‑to‑end deployment and lifecycle for AI services: CI/CD pipelines, Infrastructure as Code modules (Terraform), cloud deployment (GCP/AWS), monitoring, and incident/runbook playbooks.
- Establish and operate model evaluation, monitoring, and governance: accuracy and safety metrics, hallucination detection, drift monitoring, telemetry, alerting, and human‑in‑the‑loop controls.
- Lead vendor evaluations and POCs across commercial and open‑source LLM/agent platforms; produce comparative performance, risk, and TCO recommendations to inform adoption.
- Partner with Cybersecurity and Compliance to design PHI‑safe data handling patterns (sanitization, tokenization, least‑privilege access, audit logging) and ensure AI solutions align with relevant controls and policies.
- Create and maintain architecture diagrams, API documentation, runbooks, support documentation, and onboarding materials so solutions are maintainable and auditable.
- Mentor engineers and influence architectural standards for AI/LLM adoption across Digital Workplace; contribute reusable libraries and IaC modules to accelerate future builds.
Qualifications:
- Bachelor’s degree in Computer Science, Engineering, or equivalent practical experience.
- 8+ years professional software engineering / systems integration experience.
- Practical experience owning the complete lifecycle of LLMs and agent development.
- Strong coding experience in Python and/or TypeScript/JavaScript with production software engineering discipline.
- Experience designing and building API integrations (REST/GraphQL), webhooks, and custom connectors to SaaS applications.
- Experience with Infrastructure as Code (Terraform) and deploying services to cloud platforms (GCP/AWS).
- Experience evaluating model performance, mitigating hallucinations and bias, and implementing human‑in‑the‑loop controls.
- Working knowledge of security best practices for data‑sensitive systems; experience in healthcare or other regulated environments is strongly preferred.