About this role.
ClickUp is hiring a Staff AI Engineer to build backend infrastructure for sophisticated multi-agent AI systems. The role centers on LLM integration, agent orchestration using LangGraph-like frameworks, scalable workflow design, and rigorous AI-agent evaluation. The engineer will address privacy, secure data handling, compliance, and search integration while partnering with product, design, and frontend teams. This is a senior technical leadership role requiring deep hands-on expertise in LLM platforms, distributed backend systems, and multi-agent architecture.
Role DNA
A quick view of the complexity, pace, ownership and collaboration implied by the job description.
Job Complexity
5/5Pace & Pressure
5/5Autonomy Level
5/5Communication Load
4/5Salary analysis
Estimated compensation compared with the broader US market for similar roles.
Core skills
Skills and capabilities most closely associated with this opportunity.
Sample interview questions
I would separate agent definitions, workflow state, execution orchestration, tool access, and observability into clear services or modules. A durable state model, queue-based execution, idempotent tool calls, policy enforcement, tracing, and retry controls would provide scalability and reliability. I would also define explicit communication protocols and permissions between agents to prevent uncontrolled loops or unsafe information sharing.
I would combine offline scenario-based evaluations, deterministic unit tests for tools and workflow logic, model-graded assessments with calibration, and human review for high-risk outputs. Metrics would include task success, factuality, tool-use correctness, latency, cost, safety-policy adherence, and coordination quality. Production monitoring and sampled feedback would then feed a versioned regression suite.
I would evaluate models against the specific task requirements: reasoning quality, tool calling reliability, context capacity, latency, cost, data-handling requirements, and failure behavior. A routing layer can select models by task complexity and risk, while abstraction interfaces reduce provider lock-in. Decisions should be supported by repeatable benchmarks and monitored in production.
I would apply data minimization, tenant isolation, role-based access controls, encryption in transit and at rest, auditable tool permissions, and redaction or anonymization before model calls where appropriate. I would also define retention controls, vendor data-processing policies, prompt-injection defenses, and approval gates for sensitive actions. Privacy requirements should be validated through threat modeling and continuous security review.
I would build retrieval around high-quality ingestion, document parsing, metadata and permission-aware indexing, hybrid lexical and semantic retrieval, and reranking. Agents should receive grounded, cited context with query reformulation and filters tailored to the user's authorization scope. I would evaluate retrieval separately from generation using relevance, recall, freshness, latency, and permission-leakage metrics.
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. Every team member is expected to leverage AI daily, and we evaluate AI fluency as part of our hiring process. Join us and help redefine what’s possible. 🚀
Role Overview:
We are seeking a highly skilled Staff AI Engineer – Multi-Agent Frameworks to join our AI Platform team. In this role, you will play a pivotal part in building a cutting-edge platform that empowers our users to create and deploy sophisticated intelligent agents, with a key focus on enabling collaborative and multi-agentic behaviors. This is a backend-focused role that requires deep expertise in AI, large language models (LLMs), and orchestration software.
Key Responsibilities:
Design, develop, and maintain a robust platform to enable users to create and manage AI agents and their interactions.
Integrate and work with multiple LLMs, ensuring seamless orchestration and scalability for both individual and coordinated agent operations.
Leverage orchestration frameworks like LangGraph and others to build complex workflows and pipelines that support diverse agent functionalities, including frameworks for multi-agent coordination.
Develop and implement evaluation frameworks for testing AI agents in challenging and complex scenarios, focusing on individual performance and system-level dynamics.
Stay at the forefront of AI advancements, incorporating the latest research and technologies into our platform to enhance agent capabilities and collaboration.
Collaborate with cross-functional teams, including product managers, designers, and frontend engineers, to deliver a seamless user experience for building and deploying intelligent systems.
Address challenging AI privacy scenarios, ensuring compliance with data protection regulations and best practices within agent-based applications.
Contribute to improving search capabilities and integrating them into the AI platform to provide agents with essential information access.
Qualifications:
Proven experience working with multiple LLMs (e.g., OpenAI, Anthropic, Cohere, etc.) and understanding their strengths and limitations.
Expertise in orchestration software like LangGraph or similar frameworks used for building and managing agent workflows.
Strong background in developing evaluation frameworks for AI systems, particularly in complex testing environments.
Deep understanding of AI and machine learning fundamentals, with a focus on backend engineering.
Passion for staying updated with the latest developments in AI and applying them to real-world problems, particularly in the realm of agent technologies.
Experience with challenging AI privacy scenarios, including data anonymization, secure data handling, and compliance.
Experience with search technologies and their integration into AI systems.
Experience building or deploying Multi-Agent Frameworks or Multi-Agent Systems.
#LI-REMOTE
#LI-AK2
#LI-CC1
Equal Opportunity Employer
ClickUp is an Equal Opportunity Employer, and qualified applicants will receive consideration for employment without regard to race, color, religion, sex, sexual orientation, gender identity, or national origin.
Privacy Notice
ClickUp collects and processes personal data in accordance with applicable data protection laws. You can find further details by viewing our Global Candidate Privacy Notice.
If you are a Philippine Job Applicant, please also see our Philippine Data Privacy Notice for further details.
Visa Sponsorship
Please note we are unable to sponsor or take over sponsorship of an employment visa for roles outside of engineering and product at this time. Sponsorship for engineering and product roles is not guaranteed, but is instead based on the business needs for that specific role at that time. Please reach out to the recruiter with any questions.
Fraud Alert
ClickUp Talent Acquisition will only initiate contact via an @clickup.com email or through our official careers portal on clickup.com. We will never request fees, payments, or sensitive personal information. Please disregard any offers received outside these channels and report them to support@clickup.com.
AI Processing Notice
ClickUp may use artificial intelligence and machine learning technologies to help review and screen candidates’ employment applications against role-related criteria. These tools support, but do not replace, human decision‑making. If you have questions or need an accommodation in the recruitment process, please contact us at AskPeople@ClickUp.com.
Upload your resume now
- To unlock remote work opportunities and be discovered by global employers.
This job listing has been manually reviewed by the Jobicy Trust & Safety Team for compliance with our posting guidelines, including verification of the company's legitimacy, accuracy of job details, clarity of remote work policy, and absence of misleading or fraudulent content.
