Staff ML Engineer AI Platform & Agents

ELLKAY, LLC• US,

3d•$180,000 - $220,000•Hybrid

About The Position

Lead the design and delivery of shared AI/ML services for ELLKAY's migration, archive, connector, and interoperability products. This hands-on technical leadership role covers model development, LLM applications, governed agents, reusable serving interfaces, and engineering standards. The engineer will mentor the team and partner with Data Platform, product, clinical, and security leaders to turn pilots into measurable production capabilities. The role includes establishing shared AI architecture and evaluation and release practices, designing governed agent experiences, integrating with platform APIs, and selecting appropriate methods based on quality, latency, and cost. It also includes building reference implementations and addressing difficult production failures. Expected outcomes include agreeing on architecture and ownership boundaries and delivering reference implementations for two use cases during the first 90 days; delivering a common AI service used by two workflows and completing a measured synthetic or no-PHI pilot by six months; and demonstrating adoption across at least two product families, workflow improvement, and reproducible evaluation evidence for all production AI releases by 12 months. Targets depend on use cases, baselines, platform capabilities, and approved pilot scope.

Requirements

8+ years of relevant software/ML engineering experience, including ownership of production ML systems and technical leadership across teams.
Strong Python and SQL skills, sound software design, automated testing, and API development experience.
Experience with PyTorch, scikit-learn, or comparable ML frameworks.
Hands-on experience with model training, feature engineering, model selection, error analysis, statistical evaluation, and techniques to prevent dataset leakage.
Production experience with LLM applications, retrieval-augmented generation, embeddings, tool calling, model routing, and structured outputs.
Ability to design distributed services, cloud serving, access controls, model and prompt lifecycle management, and cost/performance tradeoffs.
Evidence of mentoring engineers and translating product needs into deliverable technical designs.
A relevant degree or equivalent practical experience is acceptable.

Nice To Haves

Healthcare integration or regulated enterprise AI experience.
MCP/tool-calling experience.
AWS and Snowflake experience.
Familiarity with HL7, FHIR, and migration or archive workflows.
Experience with LangGraph or an equivalent orchestration approach.

Responsibilities

Define shared AI architecture, model-routing approach, retrieval interfaces, tool contracts, and release criteria.
Lead design reviews and mentor the distributed ML team.
Design governed agent experiences for implementation guidance, migration recommendations, operational explanations, and archive retrieval.
Integrate with the shared agent gateway and existing platform APIs.
Enforce tenant and purpose checks, approvals for actions, asynchronous job status, and auditable tool execution.
Choose between rules, classical ML, retrieval, and LLMs using measured quality, latency, and cost.
Coordinate rollout from synthetic sandbox to approved customer pilots.
Develop reference implementations and own difficult production failures, including model regressions, retrieval errors, invalid tool actions, and latency or cost overruns.
Partner with Data Platform, product, clinical, and security leaders to turn pilots into measurable production capabilities.
Establish AI architecture, ownership boundaries, evaluation and release standards, and reusable AI services across product workflows.