Senior Full-Stack Engineer, AI Engineering

Description At TWG Group Holdings, LLC (“TWG Global”), we drive innovation and business transformation across a range of industries—including financial services, insurance, technology, media, and sports—by leveraging data and AI as core assets. Our AI-first, cloud-native approach delivers real-time intelligence and interactive business applications, empowering informed decision-making for both customers and employees. We prioritize responsible data and AI practices, ensuring ethical standards and regulatory compliance. Our decentralized structure enables each business unit to operate autonomously, supported by a central AI Solutions Group, while strategic partnerships with leading data and AI vendors fuel game-changing efforts in marketing, operations, and product development. You will collaborate with management to advance our data and analytics transformation, enhance productivity, and enable agile, data-driven decisions. By leveraging relationships with top tech startups and universities, you will help create competitive advantages and drive enterprise innovation. At TWG Global, your contributions will support our goal of sustained growth and superior returns, as we deliver rare value and impact across our businesses. The Role We're hiring a Senior Software Engineer to build agentic AI products across web, backend, and iOS. You'll own features end-to-end, from agent de [... source excerpt omitted ...] rvice, a Python agent layer, a React frontend, and a Swift iOS app in the same week. You should also have strong opinions about how to measure whether an agent is getting better. You'll work closely with product, design, and other engineers, and you'll mentor more junior teammates. Key Responsibilities: Design, build, and operate agent-based software that executes multi-step tasks with tools, memory, and stateful workflows using LangGraph or equivalent frameworks Build and maintain evaluation pipelines for LLM and agent quality: offline eval suites, regression tests, tool-call and trajectory scoring, and the dashboards and tooling that make results actionable Lead developm [... source excerpt omitted ...] e, auth, and async messaging Drive code quality, testing discipline, and engineering standards Mentor junior engineers and raise the bar through code review and design feedback Requirements 5+ years building production software at scale Hands-on experience building real LLM and agent applications, not demos. You've designed tool interfaces, orchestrated multi-step workflows, handled failure modes in agent loops, and shipped something users depend on Direct experience with agent evaluation: building golden datasets, running offline evals, scoring tool calls and trajectories, and using eval results to drive prompt, model, and architecture changes. Familiarity with frameworks like