Staff AI Engineer - AI Infrastructure & Agentic Platform

ShiftKey is a platform disrupting the way healthcare facilities find licensed and certified professionals to fill available shifts. Leveraging marketplace dynamics and deep industry knowledge, the company mitigates America’s healthcare staffing shortages by enabling direct connections between facilities and healthcare professionals. ShiftKey empowers healthcare workers to choose their own schedules, bringing more licensed professionals back into the workforce.

About the role

ShiftKey is a healthcare workforce marketplace operating in a regulated (HIPAA) environment, building toward becoming an AI-native company. This role exists to own ShiftKey’s AI infrastructure layer: the organizational knowledge platform, the infrastructure for hosting and operating AI agents in the cloud, and the retrieval layer powering both internal engineering tools and customer-facing capabilities. A retrieval stack is already in production; the next layer is in active development. You will architect and own ambitious components such as richer retrieval over organizational knowledge, agentic infrastructure, the platform API surface, and the cost-governance model for a regulated environment.

Responsibilities

• Evolve the AI knowledge platform, advancing the retrieval, indexing, and synthesis layer (currently semantic RAG + re-ranking + HyDE) into an organization-wide platform serving internal and customer-facing capabilities.
• Architect and operate agentic infrastructure on AWS, building multi-step, tool-using AI systems with cost guardrails and observability from day one.
• Design and build graph-based, relationship-aware retrieval across organizational data sources to enable multi-hop queries and agent knowledge accumulation.
• Partner with product engineering to define the AI platform API surface, translating infrastructure primitives into developer-ready abstractions.
• Build reference agent implementations (e.g., operational-incident triage, customer support) grounded in institutional knowledge.
• Own the AI infrastructure cost model: monitor compute, model, and storage spend, flag anomalies, and propose guardrails to stay within budget.

Requirements

• 7+ years of professional software engineering experience, with at least 2 years building and operating production AI/LLM application systems.
• Advanced retrieval engineering experience: hybrid search, re-ranking, query transformation, context-window management, and evaluation of retrieval quality in production.
• Working experience with agentic frameworks and multi-step reasoning loops, including tool use, iteration control, cost governance, and model routing trade-offs.
• Production-grade software engineering fluency in Go, Python, or TypeScript, with the ability to ramp into another language quickly.
• Hands-on experience operating AI workloads on AWS Bedrock or Azure AI Foundry, including identity/secrets model and model access governance.
• Hands-on Terraform experience: able to author and provision new infrastructure independently.
• Familiarity with production observability for AI systems: metrics, structured logging for model spend and latency, and evaluation harnesses.
• Understanding of HIPAA-style data-handling requirements in a regulated SaaS environment.

Benefits

• Comprehensive health, vision, and dental coverage beginning on your first day.
• Generous PTO, company-paid holidays, and flexible floating holidays.
• 100% 401(k) employer match up to 6%.
• Paid parental leave.
• Wellness support, including access to mental health resources.

Schedule

This is a fully remote position based in the United States. You should be comfortable working asynchronously and partnering with teammates in different time zones.