• Design, develop, and deploy scalable applications in our AWS environment, ensuring the implementations meet business requirements and adhere to high-quality standards. • Collaborate closely with cross-functional teams, including product managers, designers, and fellow engineers, driving seamless product development from concept to deployment. • Keep our tech stack modern and competitive by staying current with the latest industry trends and technologies. • Enhance system observability and reliability through writing tests, adding key metrics, debugging issues, and learning from incidents. • Contribute to our team's growth by assisting with resume screening and conducting interviews for new talent.

• Lead production-grade healthcare AI systems: scale distributed Python-based agents, own end-to-end delivery with real patients, in a lean team; make care accessible. • Deploy and refine AI-driven patient communication and triage systems directly with hospitals and clinics. • Architect and scale agent orchestration systems built on LLMs and agentic frameworks. • Build and maintain secure healthcare data layers with low-latency voice and video capabilities. • Scale distributed systems under real clinical load. • Work in a small team which means you own things end to end, not hand them off.

• Develop and maintain features on our Next.js (App Router) frontend using TypeScript, SWR, Tailwind, and a component-driven design system, with full internationalization (i18n) support. • Design, implement, and maintain RESTful APIs with NestJS (TypeScript) to manage authentication, data processing, billing, usage tracking, and orchestration of AI workflows. • Own backend services end-to-end: from schema design and migrations to deployment and observability, and contribute to new services as the product surface grows. • Integrate and maintain third-party SDKs and APIs that power critical product flows, including payment processing, authentication, analytics, and messaging. • Build AI agents and tools using the Claude SDK and Model Context Protocol (MCP): giving LLMs real-time access to data, APIs, and tools so they can take meaningful actions on behalf of users. • Contribute to schema design with Prisma and PostgreSQL, write and review migrations, and reason carefully about data models that evolve safely over time. • Implement and maintain feature flags, A/B experiments, and analytics events so product decisions are driven by data. • Handle incoming webhooks and asynchronous task processing with the rigor required for payment-critical and PII-handling code paths (idempotency, retries, fault tolerance). • Collaborate with AI product managers and AI specialists to translate complex requirements into robust, scalable features — and push back on complexity when a simpler path exists. • Collaborate on application deployment and help maintain our cloud infrastructure.

• Design scalable technical solutions in collaboration with local and distributed engineering teams • Partner closely with internal stakeholders and cross-functional teams to deliver high-quality features • Mentor and support junior engineers, contributing to team growth and engineering excellence • Work independently with strong ownership and adaptability to evolving business priorities • Write clean, maintainable, testable, high-quality code • Drive engineering best practices around testing, automation, and code quality • Ensure all solutions meet established quality and security standards • Participate in architecture discussions, design reviews, and code reviews • Analyze feature performance and define success metrics • Identify and troubleshoot performance bottlenecks • Apply secure coding principles and system security best practices • Contribute to technical documentation and system design artifacts