WHY BOX NEEDS YOU
Box is scaling Box AI and our internal analytics to power smarter decisions across the business.
You will design and deploy AI agents and operational solutions that strengthen both IT and business workflows. These agents will be engineered to minimize hallucinations and prioritize security in their models, data handling, and decision-making. You will also build and maintain MCP servers and developer tools that surface actionable data insights and make it easier for teams to act on them. Overall, your work will connect secure, reliable infrastructure with practical AI capabilities to accelerate informed, low-risk decision-making across the organization.
WHO YOU ARE
We are an AI-first company. This means you approach your work with a growth mindset and find ways to leverage AI to help make faster, smarter decisions that will 10X your impact at Box.
WHY BOX NEEDS YOU
Box is scaling Box AI and our internal analytics to power smarter decisions across the business.
You will design and deploy AI agents and operational solutions that strengthen both IT and business workflows. These agents will be engineered to minimize hallucinations and prioritize security in their models, data handling, and decision-making. You will also build and maintain MCP servers and developer tools that surface actionable data insights and make it easier for teams to act on them. Overall, your work will connect secure, reliable infrastructure with practical AI capabilities to accelerate informed, low-risk decision-making across the organization.
,[Design, build, and deploy AI agents that automate and improve IT and business workflows while minimizing hallucinations and ensuring reliable outputs., Implement model validation, monitoring, and fail-safe mechanisms to detect and reduce incorrect or risky agent behavior., Architect secure data handling pipelines (ingest, storage, access controls, encryption) to protect sensitive information used by models and agents., Develop and maintain MCP servers and developer tooling that surface actionable insights and make it easy for teams to query, debug, and act on model outputs., Integrate observability and telemetry (logging, metrics, tracing) for agents and infrastructure to enable rapid incident detection, root-cause analysis, and performance tuning., Build role-based APIs and interfaces that allow business and engineering teams to safely interact with agents and automated workflows., Create onboarding, documentation, and training materials to help teams adopt agents and follow best practices for secure, low-risk usage., Collaborate with security, compliance, and product teams to define policies, access controls, and approval workflows for model deployment and data use., Optimize infrastructure cost and reliability through capacity planning, fault tolerance, CI/CD pipelines, and automated testing for agent behavior and integrations., Continuously evaluate new model architectures, tooling, and defenses to improve accuracy, reduce bias, and maintain a secure, scalable AI platform., Define canonical schemas, metadata standards, and classification taxonomies to enable trusted decisions and secure data sharing between IT and business teams., Create automated metadata pipelines using AI/NLP to extract, normalize, and enrich dataset context (ontology, definitions, sensitivity, lineage), and automate metadata population, semantic matching, and lineage inference for faster cataloging., Develop AI agents and tooling that summarize dataset health, recommend joins/transformations, infer line Requirements: Python, AI, Gemini Additionally: Sport subscription, Private healthcare, Flat structure, Lunch card, International projects, Small teams, Free coffee, Bike parking, Shower, No dress code, Startup atmosphere, In-house hack days.