• Develop and refine prompts to ensure optimal performance of Large Language Models (LLMs) in healthcare applications. • Experiment with various prompt strategies and assess their impact on model responses. • Collaborate with developers and domain experts to integrate LLM capabilities into WRS Health’s EHR platforms. • Ensure prompts support accurate, context-aware responses tailored to healthcare-specific needs. • Evaluate and analyze model outputs to identify inconsistencies or areas for improvement. • Collaborate with data scientists to fine-tune models using healthcare-specific datasets. • Work closely with healthcare professionals and cross-functional teams to ensure LLMs align with user needs. • Educate internal teams on prompt engineering best practices and AI applications in healthcare. • Document prompt engineering methodologies, experiments, and outcomes for future reference. • Regularly report progress, challenges, and insights to stakeholders.

• Design and implement backend services that ingest, normalize, and persist high-volume telemetry using event-driven and MQTT-based pipelines. • Implement secure authentication and bi-directional communication for commands and diagnostics, designed for intermittent connectivity. • Integrate edge AI outputs (range prediction, health monitoring) into cloud services and surface them explainably in a Fleet Portal UI. • Architect robust MQTT communication protocols for data exchange between the eAPU and various external devices/cloud services. • Act as the technical "right-hand" to the leadership team, making pragmatic trade-offs between speed, reliability, and simplicity.

• Own the full ML lifecycle: Take projects from ideation to production, including feature engineering, model selection, deployment, and model observability and evaluation. • Translate business needs into ML solutions: Gather product requirements and translate them into robust ML system design requirements. • Build recommendation and ranking systems: Architect and launch ranking and recommendation infrastructure from scratch, initially via integrated off-the-shelf models, and evolving to targeted and customized solutions in the long term. • Solve complex problems: Work on a variety of information extraction, information storage and information retrieval problems for both structured and unstructured data. • Collaborate cross-functionally: Partner with cross-functional (product, infra, data engineering, and software engineering) teams to build robust, high-scale systems that underlie all of our data processing and ML Operations.

• Design and build distributed systems that process, enrich, and respond to billions of behavioral events per day in real time • Develop high-performance APIs and services that support advertising, identity, and intent features across the Marketing Platform • Leverage machine learning and large language models (LLMs) to analyze behavioral data, classify content, extract signals, and enable intelligent decision-making • Build intelligent agents using frameworks like LangGraph or MCP to reason over data and power user-facing insights • Design and operate data pipelines using tools like Kafka, Kinesis, and ClickHouse to support both streaming and batch workloads • Drive quality, performance, scalability, and observability across all systems you own • Collaborate cross-functionally with product managers, data scientists, and engineers to deliver customer-facing features and internal tooling • Contribute to technical leadership and mentorship of teammates.