• Lead the end-to-end development of AI-powered features, from initial prototyping to production deployment. • Integrate LLMs and ML models into existing web/mobile applications and backend APIs. • Design 'AI-first' user journeys, ensuring features like autocomplete, summarization, and intelligent search are intuitive and high-performing. • Craft, test, and optimize complex system prompts to ensure high-quality, safe, and consistent model outputs. • Build and manage Agentic workflows (using frameworks like LangChain, CrewAI, or AutoGen) to automate multi-step business processes. • Implement robust error-handling and 'fallback' logic for non-deterministic AI responses to maintain a seamless UX. • Act as the AI subject matter expert within your Product Squad, helping PMs understand what is technically feasible vs. what is 'AI hype.' • Work closely with UX/UI designers to handle AI-specific design challenges. • Participate in agile ceremonies, contributing to grooming, planning, and rapid iteration. • Develop applications that can switch seamlessly between Cloud APIs and On-Premises models.

• Develop, test, and maintain software applications. • Write clean, efficient, and well-structured code. • Work closely with product, design, and technical teams. • Participate in technical discussions and solution design. • Debug, troubleshoot, and improve existing systems. • Support code reviews and follow development best practices. • Contribute to system performance, scalability, and reliability. • Prepare technical documentation when needed.

• Own features from concept to deployment • Design, build, test, and release production-ready software • Refactor and improve existing codebases • Debug and maintain AI-generated applications • Improve scalability, maintainability, and performance • Create technical documentation and design decisions • Collaborate with globally distributed teams

• Deliver cross-cutting engineering work — platform components, refactors, integrations, and high-leverage features — at a pace achievable only through disciplined use of coding agents (Claude Code, Codex, or comparable) and modern agentic engineering practices. • Set the technical standard for the engineering organization. • Define and codify what good agentic engineering looks like at Marathon, including spec-driven development workflows, agent steering documents, custom Skills, MCP server patterns, subagent orchestration, and disciplined context engineering. • Package these as reusable skills, plugins, templates, and internal documentation that other engineers can adopt without reinventing them. • Drive architectural decisions that span Engineering, Data, and Infrastructure. • Partner with the Principal Architect and engineering leadership on systems design problems that cross team boundaries, lead ARB-level reviews, and bring strong fundamentals to API design, distributed systems, event-driven patterns, observability, and security within a HIPAA-regulated environment. • Build internal agents, MCP integrations, and RAG-backed applications where the return on investment is clear. • Apply agent development frameworks pragmatically, with appropriate evaluation, guardrails, and cost discipline. • Influence both what gets built and how it gets built. • Partner directly with engineering leaders, product partners, and internal stakeholders to shape initiative scoping, sequencing, and tradeoff decisions. • Bring product judgment and technical discernment upstream into the question of whether a problem warrants engineering investment — not just downstream into how the work is delivered. • Mentor senior and staff-level engineers across the organization. • Lead pairing sessions, design reviews, and brown-bags. • Grow agentic and AI-native engineering fluency across Engineering, Data, and Infrastructure through hands-on collaboration and visible example. • Operate as a healthcare-aware engineer. Respect PHI handling, BAA requirements, audit trails, clinical safety considerations, and regulated change management, and help teams move efficiently within these requirements.