The opportunity
At ClickUp, we're building the future of work: the first truly converged AI workspace unifying tasks, docs, chat, calendar, and enterprise search, all supercharged by context-driven AI. We are an AI-native company.
What you'll do
Design, build, and own ClickUp's AI evaluation system , including golden: datasets, LLM-as-judge and automated scorers, regression detection, and quality tracking across AI features.
Build and evolve the core agent harness , and the AI that performs well on: those evals, partnering closely with product and engineering to define what "great" looks like.
Build self-improvement loops where agents modify other agents or prompts,: rerun evals, and iterate automatically.
Benchmark new models as they're released and own model selection, routing,: and fallback strategies across providers (e.g., OpenAI, Anthropic, Google, open-weight), balancing quality, latency, and cost.
Architect, design, and implement scalable AI platform services that support: the deployment, orchestration, and lifecycle management of LLMs and other AI models.
Build and maintain robust APIs and backend systems that integrate AI-powered: features into ClickUp's core platform.
What they're looking for
- Develop infrastructure for model serving, monitoring, logging, and automated: evaluation to ensure high reliability and performance of AI services in production.
- Drive best practices in AI privacy, security, and compliance, including data: anonymization, secure data handling, and regulatory adherence.
- Collaborate cross-functionally with product, frontend, and data teams to: deliver seamless, reliable, and user-centric AI experiences.
- + years of software engineering experience, including 2+ years building production LLM or ML systems.
