machine learning engineer for enterprise content

Box is a leader in Intelligent Content Management. Its platform helps organizations collaborate, manage content lifecycles, secure critical information, transform business workflows, and apply enterprise AI. The Metadata Extraction team develops AI-powered document understanding capabilities that convert unstructured enterprise content into structured metadata using technologies such as OCR and LLM-based extraction agents.

• Design, build, deploy, and maintain production LLM agents, machine learning models, and services;
• Develop data preparation pipelines, prompt and tool designs, and agentic workflows;
• Write high-quality, maintainable, and well-tested Python code for production systems;
• Partner with Product, Software Engineering, Data, and Infrastructure teams to translate customer and business needs into ML-powered capabilities;
• Evaluate and improve agent quality using offline and online metrics, evaluation sets, experiments, and feedback loops;
• Monitor production ML systems for quality, reliability, latency, cost, and data or model drift; investigate and resolve issues;
• Contribute to the architecture of scalable services and pipelines supporting real-time and batch ML workloads;
• Create technical designs, documentation, tests, and operational runbooks;
• Share knowledge, contribute to engineering best practices, and improve code quality and operational excellence;
• Participate in an on-call rotation and triage production issues.

• 3+ Years of experience building, deploying, or operating production software, data, or machine learning systems;
• Strong Python programming skills and experience writing production-grade, readable, testable, and maintainable code;
• Practical experience with the LLM-based agent lifecycle, including data and evaluation-set preparation, prompting, tool schemas, RAG, evaluation, deployment, and monitoring;
• Experience with LLM application frameworks and libraries such as LangChain, LangGraph, PyTorch, Pydantic, Pandas, or NumPy;
• Experience calling LLM APIs such as Gemini, Claude, or OpenAI;
• Understanding of core machine learning concepts and trade-offs between model performance, reliability, latency, scalability, and cost;
• Experience building APIs, services, pipelines, or distributed systems in a cloud environment;
• Familiarity with CI/CD, observability, testing, and production support practices;
• Clear communication with technical and non-technical partners;
• Ownership mindset, ability to solve ambiguous problems, and collaborative cross-team work;
• Nice to have: MLOps tooling, model monitoring, feature stores, workflow orchestration, experiment tracking, generative AI in production, multi-provider gateways, semantic search, structured extraction, multimodal intelligent document processing workflows, GCP, AWS, Azure, Kubernetes, Terraform, SQL, BigQuery, enterprise software, security, search and retrieval, content intelligence, mentoring engineers, contributing to technical direction.

• The assigned office is expected to be used at least 3 days per week;
• Equal opportunity employer with a commitment to diversity.