• Build and ship full product features across frontend, backend, APIs and databases. • Create customer and internal workflows for onboarding, accounts, payments, rewards, travel, FX, support automation, KYC and risk. • Turn ambiguous product problems into working systems with clean UX and reliable backend logic. • Work closely with product, design, mobile, backend and AI engineers to launch fast and improve after release. • Build internal tools and automation that reduce manual work and help teams operate at scale. • Own your work beyond release: monitor, debug, learn and improve.

• Couchbase, the operational data platform for AI, empowers businesses to succeed by bringing data to life in new ways. • Major market-leading companies rely on Couchbase for mission critical operational, analytical, mobile and AI workloads. • Built to replace legacy infrastructure and fragmented data services, Couchbase empowers enterprises with a unified platform architected for performance, flexibility and global scale. • With Couchbase, organizations bring their data to life, launching game‑changing customer experiences, exploring the limitless potential of AI, and seamlessly extending applications from the cloud to the edge and beyond.

Role Description Mindrift connects specialists with project-based AI opportunities for leading tech companies, focused on testing, evaluating, and improving AI systems. Participation is project-based. What this opportunity involves: - Building a dataset to evaluate AI coding agents - how well a model handles real-world developer tasks. - Creating challenging tasks and evaluation criteria within realistic simulated environments: - Build realistic developer environments - a virtual company with codebase, infrastructure, and context (tickets, docs, conversations) that forms a believable development history. - Design tasks from intermediate states of these environments - craft the prompt, define what "solved" means, and ensure the task is solvable by an AI agent. - Write tests that verify agent solutions - accept all valid approaches and reject incorrect ones, neither too strict nor too lenient. - Iterate on tasks and tests based on QA feedback - review agent solutions, analyze failures, and refine until the evaluation is fair and robust. What this is NOT: - Not data labeling. - Not prompt engineering. - Not writing code from scratch - the agent writes most of the code; you guide and evaluate. Qualifications - 5+ years in software development. - Core stack: Python (FastAPI), JavaScript/TypeScript (React), Docker, Postgres, Kafka, Redis. - Experience writing tests (functional, integration). - English proficiency - B2+. Requirements Why this is hard: - Frontier models are already good at coding. Creating a task that genuinely challenges the best models is non-trivial. - You need to deeply understand where models fail and what scenarios reveal the difference between a good and a bad solution. - Tasks have many valid solutions - writing tests that accept all correct solutions and reject incorrect ones is harder than it sounds. Benefits - Apply → Pass qualification(s) → Join a project → Complete tasks → Get paid. - Tasks for this project are estimated to take 20 hours to complete, depending on complexity. - This is an estimate and not a schedule requirement; you choose when and how to work. - Tasks must be submitted by the deadline and meet the listed acceptance criteria to be accepted. Compensation - Up to $40/hr equivalent, depending on level and pace. - Tasks are estimated at ~20 hours each; you set your own schedule.

• Lead the technical delivery of client projects across 2-week sprint cycles — from kickoff to launch • Design and build full-stack applications in TypeScript, Node.js and React (React Native where projects call for it) • Run sprint demos and showcases directly with clients • Own day-to-day client communication over Slack and email — updates, clarifications, managing expectations • Contribute to technical proposals, scoping and estimates for new engagements • Make pragmatic architecture and technology decisions that balance speed with quality • Set the technical bar for the team — code reviews, standards, and guiding other engineers on your projects • Use AI-assisted development tooling (Claude Code, Cursor or similar) as a core part of your daily workflow