Machine Learning Engineer III, Metadata Extraction
Machine Learning Engineer III, Metadata Extraction
Requirements
3+ years of experience building, deploying, or operating production software, data, or machine learning systems.
Strong programming skills in Python, comfortable writing production-grade, readable, testable, and maintainable code.
Practical experience with the LLM based agents lifecycle including data and eval-set preparation, prompting and tool schemas, RAG, evaluation, deployment, and monitoring.
Experience with LLM application frameworks and libraries such as LangChain, LangGraph, PyTorch, Pydantic, Pandas, or NumPy, and familiar with calling LLM APIs (e.g. Gemini, Claude, OpenAI).
Understanding of core machine learning concepts and ability to make pragmatic 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 both technical and non-technical partners.
Ownership mindset, enjoys solving ambiguous problems, and works collaboratively across teams.
Nice to haves
Experience with MLOps tooling, model monitoring, feature stores, workflow orchestration, or experiment tracking.
Experience with generative AI in production: multi-provider gateways, semantic search, or structured extraction.
Experience with multimodal intelligent document processing workflows.
Experience with cloud platforms including GCP, AWS, or Azure and technologies such as Kubernetes and Terraform.
Experience with SQL and large-scale analytics (e.g. BigQuery) for quality, cost, and incident investigation.
Experience in enterprise software, security, search and retrieval, or content intelligence.
Experience mentoring engineers or contributing to technical direction.
What you'll be doing
Design, build, deploy, and maintain production LLM agents, machine learning models, and services.
Develop robust data preparation pipelines, prompt and tool design, 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 agents quality using offline and online metrics, eval 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 architecture of scalable services and pipelines supporting real-time and batch ML workloads.
Create clear technical designs, documentation, tests, and operational runbooks.
Share knowledge, contribute to engineering best practices, and help raise the bar for code quality and operational excellence.
Participate in an on-call rotation and help triage production issues when on call.
Perks and benefits
Company culture values community and in-person collaboration with a minimum of 3 days per week in office.
Diverse and inclusive workplace encouraging candidates of all backgrounds to apply.
Comprehensive benefits overview available describing life at Box (details not included here).