Applied AI Engineer

About the role

The team builds an AI automation platform that orchestrates workflows across healthcare systems, and the role experiments and improves this platform for mission-critical production use. You will design and iterate on the core components that enable autonomous AI agents to execute structured tasks across electronic health records, scheduling, and billing systems. You will partner with clinical operations to translate complex workflows into reliable automations that reduce manual effort and decision latency. You will implement robust agents that observe system state, plan multi-step actions, and adapt to edge cases without constant human oversight. You will instrument production services so that every execution is observable, debuggable, and auditable in regulated environments. You will collaborate with data and software engineers to standardize interfaces, data contracts, and error handling patterns across services. You will contribute to the architecture that balances flexibility with safety, ensuring new capabilities can be rolled out incrementally. You will participate in on-call rotations to respond to production incidents and drive improvements based on real-world telemetry.

Key facts

What you'll do

Design agentic workflows that connect large language models with healthcare operations systems to automate scheduling, prior authorizations, and data reconciliation.

Implement production-grade services that host, version, and serve AI models with strict latency, throughput, and reliability targets.

Build monitoring and observability tooling to track agent behavior, data drift, and execution success rates across distributed environments.

Partner with clinical stakeholders to define success metrics, guardrails, and escalation paths for automated decision support.

Develop integrations with electronic health record platforms, messaging systems, and identity providers using standard healthcare interoperability protocols.

Create reusable components and libraries that abstract infrastructure complexity so non-technical users can configure workflows safely.

Write tests, runbooks, and documentation that enable safe deployment, rollback, and compliance audits in regulated settings.

Analyze execution logs to diagnose failures, quantify error rates, and propose improvements to system resilience and user experience.

Contribute to open source patterns and internal tooling that standardize how autonomous agents interact with production infrastructure.

Represent the platform in cross-functional discussions, aligning roadmap priorities with reliability, scalability, and regulatory requirements.

Requirements

You show a proven track record of shipping high-quality code in challenging projects with measurable impact on reliability or efficiency.

You have experience shipping ML models to production with attention to detail and first-principles thinking toward real world deployment of intelligent systems.

You possess solid fundamentals in algorithms, data structures, and system design that enable you to build scalable and maintainable solutions.

You hold a Bachelor's or Master's degree in Computer Science, Machine Learning, or a related field that provides formal training in technical concepts.

You understand how healthcare operations structure work across clinicians, administrators, and support staff, and you design automations that reduce manual handoffs.

You are comfortable working in environments where uptime, auditability, and regulatory compliance are non-negotiable constraints.

You communicate clearly with both technical and non-technical stakeholders, translating ambiguous problems into concrete system requirements.

You take ownership of your work from design through deployment, including monitoring, incident response, and iterative improvement based on feedback.

Nice to have

Experience with distributed computing, streaming data platforms, and production ML infrastructure that helps scale workflows across many systems.

Familiarity with healthcare data standards, interoperability protocols, and compliance considerations relevant to patient information.

Background in building or operating observability, monitoring, and alerting systems for complex software services.

Practical notes

This role works on AI systems used by organizations worldwide in mission-critical production environments.

Typical interview steps

Data interviews commonly include a SQL or coding exercise, a statistics question, and a case study. Candidates may be asked to design a metric, interpret an experiment, or build a small model. Some companies give a take-home analysis. Expect questions about past projects and the business impact of your work. Interviewers often evaluate how you communicate uncertainty and business impact, not only the math. Bringing a clean write-up of a past analysis to the interview is well received.

Good to know

Machine learning systems rely on data quality, evaluation rigor, and deployment robustness.

Distributed computing and production ML experience help scale workflows across many systems.

Autonomous AI systems depend on observability, monitoring, and safety checks to operate reliably.

Core software engineering fundamentals support reliable experimentation and platform growth.

Healthcare automation relies on structured workflows and integration across disparate systems.

Questions to ask

Useful questions for the interview: what a typical week looks like, how work is assigned, what tools the team uses, and how feedback works. Asking how the role has changed recently and what the team wishes it had known when joining is also reasonable. Questions about the manager's priorities are especially valued.

Career growth

Data careers grow toward senior analyst, staff data scientist, or data engineering lead. Many professionals specialize in machine learning, analytics, or infrastructure. Cross-functional work with product and engineering teams becomes more important at senior levels. The field changes quickly, so continuous learning is part of the the job. Professionals who can translate numbers into decisions tend to advance fastest.

About the company

Healthcare operations have always depended on people to bridge the gaps that technology couldn't. It relies on complex manual work to carry out critical internal processes, yet most health systems don't have enough resources to properly automate these tasks, leaving them stuck in outdated, labor-intensive SOPs.