• Projektowanie i budowa systemów Agent AI jako część skomplikowanych, produkcyjnych platform • Współpraca z zespołami międzyfunkcyjnymi w celu zdefiniowania architektury i kierunku technicznego w całym cyklu życia, od wczesnej eksploracji do produkcji • Kierowanie i wpływanie na dyskusje dotyczące systemów i architektury, zapewniając, że rozwiązania AI są skalowalne, niezawodne, wydajne i łatwe w utrzymaniu w dłuższej perspektywie • Działanie jako zaufany doradca techniczny, kwestionując założenia, jasno formułując problemy i proponując dobrze uzasadnione rozwiązania inżynieryjne zamiast po prostu wykonywać zadania • Praca rąk na obu backendach i frontendach, z głównym zarządzaniem systemami backendowymi • Pewna współpraca w środowisku z klientem i wielu dostawcami oraz wzmacnianie naszego eksperckiego stanowiska poprzez silną wiarygodność techniczną i jasną komunikację

• Collaborate closely with Agentic AI Scientists and product teams to design, build, and deploy agentic AI systems that automate and optimize labor-intensive workflows while enabling the human workforce with new, AI-powered capabilities. • Develop and maintain full-stack software that supports agentic AI workflows. • Build user-facing interfaces and tools, implementing backend services and APIs, and writing application logic that enables agent communication, orchestration, and tool use. • Integrate AI models and agents with external systems and services via APIs, supporting testing and debugging, deploying solutions into target environments, configuring monitoring and logging, and ensuring reliable, secure execution of agentic AI systems in production. • Work with a mix of open-source models, agentic frameworks, and proprietary commercial AI services. • Contribute to the development of approaches for securing agentic workflows and for evaluating system behavior with respect to accuracy, performance, reliability, and mission impact. • Help ensure that AI systems adhere to ethical guidelines and principles of transparency, accountability, and fairness. • Conduct applied research, develop prototypes, and evaluate and document results, including contributing to technical reports, publications, or conference presentations.

• 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.