- Design, build, and ship agentic AI features end to end, from detection and decision logic through safe action execution, in a cross-functional agile environment - Ground agent behavior in deterministic rules engines and governed data so every agent explains its reasoning and never acts outside permitted boundaries - Build and operate the LLM layer, including prompt architecture, structured outputs, confidence scoring, timeouts, and rules-only fallback paths - Implement safe patterns for agent actions, including idempotent operations, undo windows, retries with backoff, and immutable audit logging - Develop statistical detection and baseline logic that turns workforce data into ranked, explainable findings with business impact attached - Manage inference cost, latency, and model selection from development through production - Partner with QA on evaluation suites, shadow-mode rollouts, and the trust metrics that gate every agent capability, and mentor junior engineers along the way - Operate independently, setting priorities and goals while continuing to learn and grow technically

• Build end-to-end applications that incorporate generative AI capabilities into real user workflows • Develop scalable backend services, APIs, and integrations using modern engineering practices • Build responsive and maintainable frontend experiences using modern frameworks • Design modular system architectures that support scalability, reliability, and long-term maintainability • Integrate LLMs and other AI tools into production applications with appropriate safeguards and monitoring • Optimize prompt flows, data pipelines, and system interactions for consistency and performance • Translate business requirements into technical solutions and make strong implementation trade-offs • Own features from ideation through development, testing, deployment, and iteration • Reuse and adapt proven solutions where appropriate to accelerate delivery • Continuously improve product quality based on performance data, feedback, and operational learnings

Role Description We are looking for a Senior Full Stack AI Engineer to design, build, and scale production-grade applications powered by generative AI. This role is focused on delivering real products, not just prototypes. The ideal candidate is a strong end-to-end builder who can make sound architectural decisions, integrate AI capabilities into usable systems, and balance fast delivery with long-term maintainability. - Build end-to-end applications that incorporate generative AI capabilities into real user workflows - Develop scalable backend services, APIs, and integrations using modern engineering practices - Build responsive and maintainable frontend experiences using modern frameworks - Design modular system architectures that support scalability, reliability, and long-term maintainability - Integrate LLMs and other AI tools into production applications with appropriate safeguards and monitoring - Optimize prompt flows, data pipelines, and system interactions for consistency and performance - Translate business requirements into technical solutions and make strong implementation trade-offs - Own features from ideation through development, testing, deployment, and iteration - Reuse and adapt proven solutions where appropriate to accelerate delivery - Continuously improve product quality based on performance data, feedback, and operational learnings Qualifications - Strong full stack engineering experience, ideally 5+ years - Proficiency in backend development with technologies such as Node.js, Python, or similar - Strong frontend experience with frameworks such as React or comparable modern tools - Experience building and consuming APIs, working with databases, and deploying on cloud platforms - Hands-on experience integrating generative AI into production applications - Practical understanding of prompt engineering and AI system limitations, including failure modes and edge cases - Proven ability to design systems that scale beyond MVP and remain maintainable over time - Strong understanding of software architecture, system design, and engineering best practices - Demonstrated experience shipping multiple production-grade products or platforms - Ability to combine traditional software engineering discipline with modern AI-driven workflows - Experience working independently with strong ownership and product mindset Benefits - Opportunity to build impactful AI-powered products used in real production environments - High ownership across architecture, implementation, and delivery - Role suited for engineers who enjoy both product thinking and technical depth - Chance to shape scalable systems early and influence long-term engineering quality - Fast-paced environment with a strong emphasis on execution and practical outcomes - Meaningful work at the intersection of full stack engineering and applied AI

• Define and drive a long-term AI/ML architectural vision • Own the strategic roadmap for Twilio’s ML/AI Ops platform and tooling • Evaluate and implement modern LLM architectures • Lead architecture for agentic AI systems • Transition seamlessly from high-level strategic communication to deep-dive code reviews • Partner closely with Product Management