高级平台工程师
Senior Platform Engineer
我们是谁:
Interra Health 是一家快速发展的医疗技术公司,正在改变医护人员和患者在开药过程中的体验。Interra Health 由 DoseSpot、Arrive Health 和 pVerify 合并而成,为医护人员提供可信赖的资格验证、实时保险和定价洞察、处方工具以及药房透明度,帮助医护人员做出明智决策,让患者更清晰、更负担得起地获得合适的药物。依托强劲的市场势头和对连接护理未来的大胆愿景,Interra Health 提供了加入一个创新、以使命为导向的团队的机会,这些团队在软件和医疗保健的交汇点工作,以减少摩擦、改善可及性,并让每个人的医疗体验变得更好。
我们是谁:
Interra Health 是一家快速发展的医疗技术公司,正在改变医护人员和患者在开药过程中的体验。Interra Health 由 DoseSpot、Arrive Health 和 pVerify 合并而成,为医护人员提供可信赖的资格验证、实时保险和定价洞察、处方工具以及药房透明度,帮助医护人员做出明智决策,让患者更清晰、更负担得起地获得合适的药物。依托强劲的市场势头和对连接护理未来的大胆愿景,Interra Health 提供了加入一个创新、以使命为导向的团队的机会,这些团队在软件和医疗保健的交汇点工作,以减少摩擦、改善可及性,并让每个人的医疗体验变得更好。
职位描述:
Interra Health 正在工程领域扩展人工智能:开发速度、运营韧性、自动化、可观测性和安全交付,高级平台工程师是将这一雄心转化为实际系统的实干者。向平台与运营总监汇报,该职位负责设计、实现和运营人工智能驱动的平台功能:MCP 服务器配置和可靠性、LLMOps/GenAIOps 工具、安全模型集成模式,以及这些功能运行的底层 Azure 云基础设施。
这是一个个人贡献者职位,不是管理岗位。你将与首席 AI 平台工程师密切合作,该工程师负责 AI 赋能路线图和团队,同时与负责核心 Azure 平台的工程师协作,但你将直接负责构建、加固和运营这些系统。
查看英文原文
Who We Are:
Interra Health is a fast-growing healthcare technology company transforming how providers and patients navigate the prescription journey. Formed through the merger of DoseSpot, Arrive Health, and pVerify, Interra Health delivers trusted eligibility, real-time coverage and pricing insights, prescribing tools, and pharmacy transparency at the point of care—helping providers make informed decisions and patients access the right medications with greater clarity and affordability. Backed by strong market momentum and a bold vision for the future of connected care, Interra Health offers the chance to join an innovative, mission-driven team working at the intersection of software and healthcare to reduce friction, improve access, and make the healthcare experience better for everyone.
Who We Are:
Interra Health is a fast-growing healthcare technology company transforming how providers and patients navigate the prescription journey. Formed through the merger of DoseSpot, Arrive Health, and pVerify, Interra Health delivers trusted eligibility, real-time coverage and pricing insights, prescribing tools, and pharmacy transparency at the point of care—helping providers make informed decisions and patients access the right medications with greater clarity and affordability. Backed by strong market momentum and a bold vision for the future of connected care, Interra Health offers the chance to join an innovative, mission-driven team working at the intersection of software and healthcare to reduce friction, improve access, and make the healthcare experience better for everyone.
The role:
Interra Health is scaling AI across engineering: developer velocity, operational resilience, automation, observability, and secure delivery, and the Senior Platform Engineer is the hands-on builder who turns that ambition into working systems. Reporting to the Director, Platform & Operations, this role owns the design, implementation, and operation of AI-enabled platform capabilities: MCP server configuration and reliability, LLMOps/GenAIOps tooling, secure model integration patterns, and the underlying Azure cloud infrastructure those capabilities run on.
This is an individual-contributor role, not a people-management seat. You will partner closely with the Lead AI Platform Engineer, who owns the AI enablement roadmap and team, and with the engineers who run the core Azure platform, but you carry direct, hands-on responsibility for building, hardening, and operating the AI layer itself, from infrastructure as code and CI/CD through to production monitoring, security, and compliance for AI workloads.
The right person has deep DevOps and cloud engineering fundamentals paired with genuine, practical fluency in applying AI to real infrastructure and developer-experience problems, someone who’d rather ship a working integration than write another proposal about one.
What you'll do:
- Design, build, and operate secure, scalable, highly available Azure infrastructure underpinning both core platform services and AI workloads, using Infrastructure as Code (Terraform).
- Configure, secure, and operate MCP servers and related AI integration points, including access patterns, reliability, and lifecycle management, for enterprise use.
- Build and operationalize AI-enabled capabilities, including internal engineering assistants, workflow automation, infrastructure insights, and incident-response support, applying practical LLMOps/GenAIOps practices for evaluation, monitoring, logging, cost management, and access control.
- Implement and continuously improve CI/CD pipelines in GitHub Actions and DevSecOps practices, integrating security and compliance into AI and infrastructure deployment workflows from the ground up.
- Own observability and reliability for AI and platform services, applying SRE principles such as SLOs, incident response, and blameless postmortems.
- Partner with the Lead AI Platform Engineer to implement the AI platform roadmap, building the reusable patterns, guardrails, and “paved road” solutions other engineering teams adopt.
- Evaluate, pilot, and support adoption of AI coding assistants and platform tooling across the engineering AI landscape, including GitHub Copilot, M365 Copilot, and other emerging AI dev tools, with a build-versus-buy mindset balancing speed, cost, security, and long-term maintainability.
- Participate in Agile ceremonies, track and prioritize work in Jira, and influence release planning and architectural decisions.
- Participate in on-call rotations and provide Level 3 support for production platform and AI systems.
- Contribute to internal documentation, runbooks, and knowledge-sharing so AI and platform practices scale beyond any one person.
What you'll bring:
- Bachelor’s degree in Computer Science, Engineering, or a related field, or equivalent practical experience, plus 6+ years of hands-on experience in DevOps, Cloud Engineering, or Site Reliability Engineering.
- Deep expertise in Microsoft Azure, including infrastructure as code, networking, identity/access, DNS, and load balancing.
- Practical, hands-on experience applying AI, GenAI, or automation tooling to engineering workflows, developer productivity, or production systems, such as LLMOps/GenAIOps, model gateways, RAG patterns, agent frameworks, or AI observability.
- Advanced proficiency with Terraform, containerization and orchestration (Docker, Kubernetes), and CI/CD platforms such as GitHub Actions.
- Proficient in scripting or programming languages (e.g., Python, PowerShell).
- Hands-on comfort with Jira and Agile workflows, and strong understanding of secure and compliant engineering practices: secrets management, access controls, auditability, and risk-aware implementation.
- Comfortable working autonomously in ambiguous situations, driving clarity through experimentation and iteration in a fast-paced, post-merger environment.
- Excellent communication, able to tailor messaging across engineering and business audiences.
Nice to Have
- Experience in healthcare technology, regulated SaaS, or HIPAA / HITRUST / SOC 2 environments.
- Direct MCP server implementation or administration experience.
- Cloud cost optimization or enterprise platform modernization experience.
Interra Health is an Equal Employment Opportunity/Affirmative Action employer and all qualified applicants will receive consideration for employment without regard to race, color, religion, sex, age, national origin, protected veteran status, disability status, sexual orientation, gender identity or expression, marital status, genetic information, or any other characteristic protected by law.