• Architect and build a multi-agent system in production — one capable of safely operating across a business's core tools (ERP, CRM, spreadsheets, calendars, email, analytics, compliance systems) • Build and maintain MCPs (Model Context Protocol integrations) that connect the harness to real business systems • Own production system concerns end-to-end: reliability, observability, permissions, and safe workflow execution — this is a system that will take real actions on customers' data, and the bar for getting it right is high • Since there's no existing playbook here, you'll define scope, make the call on tradeoffs, and drive execution with minimal oversight • Design for the user, not just the architecture — a product-first mindset that prioritizes how this actually gets used over what's technically interesting to build • Proactively identify and raise risks or open questions before they become blockers, and bring structured solutions, not just problems • Keep pace with a fast-moving space — agent frameworks, harness toolkits, MCP standards — and bring in better approaches as they emerge rather than waiting to be told • Work hands-on with tools like Claude Code as part of your own build process

• Architect and ship an agentic page builder • Design autonomous deployment and optimization pipelines • Build AI infrastructure powering merchant-facing workflows • Write code, design systems, and drive architecture decisions • Own outcomes and partner closely with the Engineering Lead and Product Lead • Focus on building a storefront system collaboratively with AI agents

• Owns client-specific quality programs, performance metrics, and escalations while leading team development and cross-functional coordination. • Set client QA strategies (sampling design, audit methods, acceptance thresholds) and adapt to scope/volume changes. • Run root-cause analyses; drive CAPA plans with owners, timelines, and effectiveness checks. • Plan training & certification for raters/annotators and coordinators; track completion and impact. • Maintain dashboards (throughput, accuracy, productivity, cost) and convert insights into actions. • Manage client escalations; present options, trade-offs, and recovery paths. • Standardize SOPs, templates, and checklists; remove bottlenecks. • Pilot small automations (macros, templates, RPA/API handoffs) with Ops Tech; scale wins. • Coach teams on tools, workflows, and QA craft. • Ensure compliance/security across data handling and platform access.

• Design and develop machine learning models and systems for various aspects of the localization (translation) and business workflow processes • Take ownership of key projects from definition to deployment, ensuring that they meet technical requirements and maintain momentum and direction until delivery • Experiment with and evaluate classical ML and LLM-based approaches (including prompt/context engineering, retrieval-augmented generation, and agentic workflows) to identify effective solutions for business problems • Perform statistical analysis based on experimental and test results to drive measurable performance improvements • Package and deploy machine learning systems using appropriate techniques and technologies