Ada Health

• Refine and scale our patented hybrid engine, focusing on the interface between LLM-based reasoning and probabilistic logic. • Write and deploy high-availability production code in Java and Python, ensuring adherence to security and scalability standards. • Maintain and extend our internal evaluation and validation frameworks, including synthetic data generation, automated metric tracking, and model explainability. • Work with Medical Experts and AI Engineers to translate complex medical requirements into technical specifications. • Provide technical documentation of AI components for stakeholders and regulatory compliance (e.g. SaMD).

• Act as a hands-on technical lead for the squad, contributing to code (Kotlin/Spring Boot/React), reviewing PRs, and driving architectural decisions. • Ensure the reliability and scalability of our client-facing integration layer (SDKs, APIs, SSO). • Participate in the on-call rotation and lead incident response for the team’s services, ensuring high availability for our clients. • Champion and drive engineering best practices. • Manage a small team of engineers; responsible for 1:1s, performance feedback, and career growth planning. • Foster a strong culture of ownership where engineers feel empowered to deliver high-quality work. • Collaborate with stakeholders to align individual goals with company objectives. • Collaborate with Product Management to estimate complex integration projects and establish realistic delivery timelines. • Serve as a technical voice in conversations with enterprise clients when deep technical expertise is required (e.g. integration scoping). • Own the delivery process for the team, ensuring smooth sprints and predictable release cycles and on-time delivery of initiatives.

• Extend and enhance our existing, general-purpose E2E test automation framework (Kotlin and JavaScript-based) to ensure robust coverage for our new conversational AI product. • Develop new, service-level test automation using Python to support your team's deployment pipeline and product stack. • Develop and execute novel testing strategies specifically for conversational AI and LLM-based features, focusing on performance, accuracy, and user interaction quality. • Champion a 'whole-team' approach to quality, coaching and mentoring engineers, designers, and product managers in testing and risk-based analysis. • Continuously test throughout the entire SDLC, from idea and design to code and production, using a smart mix of exploratory and automated testing techniques. • Collaborate with engineers to identify and mitigate integration risks at the API and system level, thinking deeply about how our services interact. • Document and report testing outcomes clearly, ensuring all documentation and approaches meet regulatory and compliance standards while proactively improving compliance procedures. • Drive the internal quality community, actively share your knowledge, and help raise the bar for testing and quality across the entire engineering team.