Wait, What Do You Do?

<div class="ace-line"> <div class="ace-line" data-node-type="line"> <div class="page" data-page-number="1" data-loaded="true"> <div class="textLayer"> What is Box? Box (NYSE:BOX) is the leader in Intelligent Content Management. Our platform enables organizations to fuel collaboration, manage the entire content lifecycle, secure critical content, and transform business workflows with enterprise AI. We help companies thrive in the new AI-first era of business. Founded in 2005, Box simplifies work for leading global organizations, including JLL, Morgan Stanley, and Nationwide. Box is headquartered in Redwood City, CA, with offices across the United States, Europe, and Asia. By joining Box, you will have the unique opportunity to continue driving our platform forward. Content powers how we work. It’s the billions of files and information flowing across teams, departments, and key business processes every single day: contracts, invoices, employee records, financials, product specs, marketing assets, and more. Our mission is to bring intelligence to the world of content management and empower our customers to completely transform workflows across their organizations. With the combination of AI and enterprise content, the opportunity has never been greater to transform how the world works together and at Box you will be on the front lines of this massive shift. Why Box needs you: We are looking for a Machine Learning Engineer to design, build, and operate reliable machine learning systems that deliver meaningful product impact at enterprise scale. In this role, you will combine strong software engineering and applied machine learning skills to take solutions from idea through production. You will work closely with engineering, product, data, and infrastructure partners to develop scalable ML and agentic capabilities, improve model quality, and ensure that systems are secure, observable, and dependable for Box customers. The Metadata Extraction team builds AI-powered capabilities that transform unstructured enterprise content into structured, usable metadata. The team works on the platform and machine learning layer of document understanding, developing and operationalizing technologies such as OCR and LLM-based extraction agents. These capabilities help understand document layout, tables, handwriting, semantic content, and other complex information within enterprise documents. As a Machine Learning Engineer, you will build reliable, scalable systems that support the development, evaluation, deployment, and operation of these AI capabilities. You will collaborate with engineers, product partners, and adjacent platform teams to bring document intelligence features to Box customers at enterprise scale. What you'll do: <ul> <li>Design, build, deploy, and maintain production LLM agents, machine learning models and services.</li> <li>Develop robust data preparation pipelines, prompt and tool design, and agentic workflows.</li> <li>Write high-quality, maintainable, and well-tested Python code for production systems.</li> <li>Partner with Product, Software Engineering, Data, and Infrastructure teams to translate customer and business needs into ML-powered capabilities.</li> <li>Evaluate and improve agents quality using appropriate offline and online metrics, eval sets, experiments, and feedback loops.</li> <li>Monitor production ML systems for quality, reliability, latency, cost, and data or model drift; investigate and resolve issues as needed.</li> <li>Contribute to the architecture of scalable services and pipelines that support real-time and batch ML workloads.</li> <li>Create clear technical designs, documentation, tests, and operational runbooks.</li> <li>Share knowledge, contribute to engineering best practices, and help raise the bar for code quality and operational excellence.</li> <li>Participate in an on-call rotation and help triage production issues when on call.</li> </ul>   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. <ul> <li>You have 3+ years of experience building, deploying, or operating production software, data, or machine learning systems.</li> <li>You have strong programming skills in Python and are comfortable writing production-grade, readable, testable, and maintainable code.</li> <li>You have practical experience with the LLM based agents lifecycle: data and eval-set preparation, prompting and tool schemas, RAG, evaluation, deployment and monitoring.</li> <li>You have experience with LLM application frameworks and libraries, such as LangChain, LangGraph, PyTorch, Pydantic, Pandas, or NumPy, and are comfortable calling LLM APIs (e.g. Gemini, Claude, OpenAI).</li> <li>You understand core machine learning concepts and can make pragmatic trade-offs between model performance, reliability, latency, scalability, and cost.</li> <li>You have experience building APIs, services, pipelines, or distributed systems in a cloud environment.</li> <li>You are familiar with CI/CD, observability, testing, and production support practices.</li> <li>You communicate clearly with both technical and non-technical partners.</li> <li>You have an ownership mindset, enjoy solving ambiguous problems, and work collaboratively across teams.</li> </ul> Nice to have: <ul> <li>Experience with MLOps tooling, model monitoring, feature stores, workflow orchestration, or experiment tracking.</li> <li>Experience with generative AI in production: multi-provider gateways, semantic search, or structured extraction.</li> <li>Experience with multimodal intelligent document processing workflows.</li> <li>Experience with a major cloud platform, including GCP, AWS, or Azure, and technologies such as Kubernetes and Terraform.</li> <li>Experience with SQL and large-scale analytics (e.g. BigQuery) for quality, cost, and incident investigation.</li> <li>Experience in enterprise software, security, search and retrieval, or content intelligence.</li> <li>Experience mentoring engineers or contributing to technical direction.</li> </ul>   Methodology <ul> <li>Agile management - Scrum</li> <li>Issue tracking tool -Jira</li> <li>Knowledge repository - GitHubEnterprise</li> <li>Code reviews - GitHubEntreprise </li> <li>Version control system - GIT</li> </ul>   BENEFITS Check out the <a href="https://careers.box.com/en/life-at-box/" target="_blank" data-attrib-id="link-eebb7374-25f3-4949-b45f-64f46cc8f23d">overview of Life at Box</a> which include general perks and benefits. Box lives its values, with community and in-person collaboration being a core part of our culture. Boxers are expected to work from their assigned office a minimum of 3 days per week. Your Recruiter will share more about how we work and company culture during the hiring process. At Box, we believe unique and diverse experiences benefit our culture, our products, our customers, our company, and our world. We aim to recruit a passionate, high-performing workforce that reflects the world we live in. If you are head-over-heels about this role but unsure if you meet all the requirements, we encourage you to apply! EQUAL OPPORTUNITY We are an equal opportunity employer and value diversity at our company. We do not discriminate on the basis of race, religion, color, national origin, gender, sexual orientation, age, marital status, veteran status, disability, and any other protected ground of discrimination under applicable human rights legislation. For details on how we protect your information when you apply, please see our <a href="https://cloud.app.box.com/v/BoxPersonnelPrivacyNotice" target="_blank" data-attrib-id="link-2f2015c1-154d-4eca-934b-6817d26cf18c">Personnel Privacy Notice</a>. For more details on how Box Poland protects your information, please see our <a href="https://cloud.box.com/s/tyclibn73pmofpdub2x65639ykknbiwj" target="_blank" data-attrib-id="link-4b65ca49-51b7-483f-9f2f-9d7f02e450bc">Supplemental Personnel and Candidate Privacy Notice</a>.  #LI-hybrid #LI-OB1 </div> </div> </div> </div>

Machine Learning Engineer III, Metadata Extraction