Machine Learning Engineer III, Metadata Extraction

Role overview Build and operate machine learning systems that turn complex enterprise documents into structured, usable information. You’ll work across document understanding, including OCR and language-model-based extraction, taking capabilities from development and evaluation through production while partnering with engineering, product, data, and infrastructure teams.

Responsibilities - Develop, deploy, and maintain machine learning models, language model agents, and supporting services. - Build data preparation pipelines and design prompts, tools, and agent workflows for document extraction. - Measure and improve model quality through evaluation sets, experiments, metrics, and feedback. - Monitor production systems for reliability, latency, cost, and changes in data or model behavior; investigate issues and participate in on-call support. - Help design scalable services for real-time and batch workloads, and provide tests, documentation, and operational runbooks. - Work with partner teams to shape customer needs into production capabilities and share engineering practices.

Requirements - At least 3 years of experience building, deploying, or operating production software, data, or machine learning systems. - Strong Python skills, including writing readable, testable, maintainable production code. - Practical experience with the lifecycle of language-model-based agents, including data and evaluation preparation and prompting. - Clear communication with technical and non-technical partners, collaborative working habits, and an ownership mindset for ambiguous problems.

Nice to have - Experience with MLOps, model monitoring, feature stores, workflow orchestration, or experiment tracking. - Production generative AI work, such as semantic search or structured extraction, and familiarity with multimodal document processing. - Experience with a major cloud provider, Kubernetes, Terraform, SQL, or large-scale analytics. - Background in enterprise software, security, search, retrieval, or content intelligence; mentoring or technical direction experience.

Benefits and work setup The role follows a hybrid schedule, with at least three days per week in an assigned office. General employee benefits are mentioned, but specific benefit details are not provided.