Senior Principal Agentic TechnologistArtera Corporation • Seattle, Washington, United States
Senior Principal Agentic Technologist
Artera Corporation
- Seattle, Washington, United States
- Seattle, Washington, United States
À propos
Define Artera's reference architecture for AI agents Establish design patterns for multi-agent orchestration, tool use, memory management, and human-in-the-loop workflows tailored to healthcare operations Own technical decisions on agent decomposition, communication patterns, and failure handling for mission-critical healthcare workflows Evaluate and integrate emerging agentic AI capabilities as they become available Drive continuous improvements to Artera's operational excellence and security posture
Scale-Out Enablement for Builder Teams
Design and maintain the AI development infrastructure — including AI coding skills, structured memory, MCP server tooling, and cross-customer pattern libraries — that enables multiple teams to build customer-specific agent workflows independently and consistently Work backwards from customer outcomes: design and consume production evaluation systems that measure how agents actually perform for each customer, derive actionable insights from those evaluations, and feed improvements back into shared development infrastructure as codified best practices Codify proven agent development patterns (intent expression, evaluation-driven development, semantic data discovery) into reusable templates and golden paths that keep pace with industry prescriptive guidance Define the boundaries between shared platform capabilities (security, compliance, observability, evaluation frameworks) and team-owned customization layers (per-customer prompts, tools, orchestration) Establish knowledge-compounding mechanisms so that what one team discovers — or what production evaluation reveals — reaches every other team through structured repositories, automated pattern discovery, and contextual delivery at the moment of relevance Provide architectural mentorship and review that ensures teams build agents using intent-based design rather than procedural encoding, and that evaluation criteria are defined before agent construction begins
Security — Shift-Left by Default
Embed security into the earliest stages of the development lifecycle through automated threat modeling, policy-as-code, and secure-by-default infrastructure patterns Define guardrails for agent permissions, data access scoping, and least-privilege execution in multi-tenant healthcare environments Own the security architecture for agent-to-agent communication, secrets management, and PHI handling within agentic workflows Partner with security and compliance teams to ensure agent behaviors remain auditable and aligned with healthcare data protection requirements
Observability & Operability
Design observability architecture for agentic systems — tracing agent reasoning chains, monitoring tool invocations, and measuring outcome quality Define SLOs, error budgets, and operational runbooks for agent-powered workflows Establish patterns for graceful degradation, circuit breaking, and fallback behaviors in agent systems Design evaluation frameworks that measure agent effectiveness from the customer's perspective — not just system health, but whether patients achieved their intended outcomes (appointment scheduled, question answered, referral completed) Close the feedback loop between production evaluation insights and development practices, ensuring that patterns which improve customer outcomes are systematically propagated to all builder teams Ensure operational readiness criteria are met before any agent workflow reaches production
DevOps & Engineering Excellence
Raise the bar on CI/CD practices: define pipeline standards, deployment strategies, and infrastructure-as-code patterns for agent workloads Drive adoption of trunk-based development, automated testing (unit, integration, end-to-end agent evaluation), and continuous deployment Establish engineering quality standards including code review expectations, architecture decision records, and technical debt management Define and maintain AI-assisted development workflows — including structured project memory, tool-augmented sessions, and automated pattern delivery — that accelerate onboarding and reduce tribal knowledge dependencies Mentor engineers across the organization, conduct architecture reviews, and build a culture of operational ownership
Technical Leadership & Strategy
Serve as Artera's primary technical liaison with critical external vendors, maintaining alignment with their roadmap and prescriptive guidance Influence product strategy with a deep understanding of what agentic AI can deliver for healthcare operations Make high-judgment calls on build-vs-buy, technology selection, and architectural trade-offs Represent Artera's technical vision externally through publications, conference talks, and community engagement
Basic Qualifications
12+ years of software engineering experience with increasing scope and technical leadership responsibility Deep expertise in distributed systems design — building and operating large-scale, highly available, fault-tolerant services Extensive hands-on experience with AWS services (compute, networking, identity, databases, serverless, AI/ML) Demonstrated ability to define and drive technical strategy across multiple engineering teams Track record of designing platform-level abstractions that enable other teams to deliver independently Experience establishing and scaling DevOps, CI/CD, and infrastructure-as-code practices across an engineering organization Strong written and verbal communication skills with the ability to influence without authority at all organizational levels
Preferred Qualifications
Experience with AI/ML systems in production — particularly LLM-based applications, agent frameworks, or multi-agent orchestration Familiarity with AWS AgentCore, Amazon Bedrock, or equivalent agent infrastructure platforms Healthcare industry experience including HIPAA compliance, BAA requirements, and PHI data handling in cloud environments Background in platform engineering for multi-tenant SaaS products Experience with security architecture in regulated industries — threat modeling, policy-as-code, zero-trust patterns Experience designing evaluation and feedback systems for AI/ML applications that connect production performance back to development practices History of publishing technical content, speaking at conferences, or contributing to open-source projects
$220,000 - $300,000
Compétences linguistiques
- English
Avis aux utilisateurs
Cette offre provient d’une plateforme partenaire de TieTalent. Cliquez sur « Postuler maintenant » pour soumettre votre candidature directement sur leur site.