Ezra

Role Description As an AI-First Lead Engineer, you will own the end-to-end design, quality, and reliability of EZRA’s AI capabilities, shaping how AI powers our product experience. Reporting to the VP of Engineering, you will partner cross-functionally to deliver scalable, safe, and high-performing AI solutions that drive measurable user impact. A core focus of this role is leading EZRA’s fully AI-augmented development that represents a deliberate departure from the approach taken traditionally. This stream needs a different kind of developer: someone comfortable directing AI tools, thinking architecturally, and producing clear recommendations, not just code. You will help define how this way of working takes shape at EZRA, figuring out multi-agent patterns and long-running pipelines alongside leadership rather than waiting for a playbook to exist. What You'll Do - Define and lead the design of AI solutions, including model selection, prompting strategies, orchestration patterns, and fallback mechanisms. - Own AI evaluation frameworks, establishing quality metrics and driving continuous improvement through experimentation and iteration. - Implement and maintain safety guardrails, mitigating risks such as prompt injection, data leakage, and unsafe outputs. - Optimize AI systems for performance, latency, cost, and reliability, including observability and incident response readiness. - Provide technical leadership, mentoring engineers and setting best practices for AI-enabled development across teams. - Lead AI-augmented development in the Reimagine stream, directing AI tools architecturally and translating outputs into clear, defensible technical decisions. - Design and evolve multi-agent patterns and long-running pipelines from first principles, working alongside leadership in a genuinely greenfield environment. - Critically evaluate AI-generated code for correctness, security, and enterprise suitability for shipping solutions fast without cutting corners on quality. Qualifications - 8+ years of engineering experience, including 5+ years delivering ML/AI solutions into production environments. - Strong proficiency in Python and hands-on experience with modern ML/LLM tooling, orchestration frameworks, and APIs. - Experience designing and implementing evaluation frameworks with measurable quality metrics. - Practical knowledge of AI safety risks and mitigation techniques (e.g., hallucinations, prompt injection, data leakage). - Experience optimizing systems for performance, cost efficiency, and scalability in production environments. - Experience working with cross-functional teams to translate product requirements into technical solutions. - Strong TypeScript/Node fundamentals: able to critically evaluate AI-generated code, not just ship it. - Actively building with LLMs already: shipping product features, agentic workflows, or clearly headed there fast. - Strong judgment on the speed/quality/security trade-off, particularly in an enterprise context where corners cannot be cut. - Comfortable being early: you experiment constantly, have opinions, and can help define patterns rather than waiting for a playbook to exist. Benefits - Your Own World-class coach to help you grow personally and professionally. - Coaching for Friends and family because coaching is a gift worth passing on. - Charity Days to support the causes close to your heart - because doing good feels good. - Learning Budget to fuel your curiosity. If it helps you grow, we’re in. - Weekly Wellbeing Hour just for you. No meetings. No emails. Just space to breathe, reflect, or reset. - Regional benefits flex to fit your location and lifestyle. - A welcoming place to do your best work. Comfortable, collaborative and inclusive.