Stand Insurance - ML Engineer, Data Pipeline
Requirements
• Strong ML and Data Science fundamentals with production experience • Computer vision (2D/3D, generative models, point clouds, remote sensing) • Experience building systems for annotation and data labeling • Comfort operating and improving real-world pipelines • Structured problem-solving and systems thinking • Clear written communication and cross-functional collaboration • High ownership mindset with weekly metric accountability • Predictive labeling, self-supervised or HITL systems • Multimodal ML or agentic workflows (LLMs + CV) • Experience writing SOPs, dashboards, and operational tooling • Experience managing annotation vendors or distributed teams • Temporal change detection or geospatial data systems • Exposure to insurance, risk modeling, or climate data
Responsibilities
• 1. Pipeline Operations & Reliability • Own day-to-day annotation pipeline health • Build escalation systems and failure categorization frameworks • Transition execution from manual ops → automated systems • 2. Quality Instrumentation • Build validation systems anchored on downstream model metrics • Develop anomaly detection models for annotation • Reduce manual QA burden through automation • 3. Vendor & Annotator Performance • Define performance metrics (quality, throughput) • Build training systems and feedback loops • Scale vendor operations • 4. Computer Vision & ML Systems • Own the automation roadmap • 2D/3D modeling, characterization, reconstruction • Predictive labeling and difficulty routing systems
Benefits
• $185K – $235K • Offers Equity • Upload your resume here to autofill key application fields. • Drop your resume here! • Parsing your resume. Autofilling key fields... • or drag and drop here • You’re building a pipeline to assess hail damage to properties. Two data labeling teams run QA (first-round QA) on a portion of machine-generated digital twins of properties (roof geometry, materials, nearby structures, etc.). A downstream model uses these twins to simulate hail impact and predict damage severity. A third team performs second-round QA, but this QA can only review ~40% of first-round volume. Observations: Annotator first-round agreement between the two teams on the digital twin is high (~85% on average across all label types) However, when you run the model: ~30% of twins that went through the two rounds of QA still produce materially different damage outcomes QA backlog is growing Constraints: The damage assessment model is fixed You cannot increase QA capacity Task: You need to improve confidence that QA matches are aligning in damage output stats. To do so, overhaul the framework. Some things to think about: How would you decide which samples go to QA? Be concrete. How does your strategy account for the fact that annotation errors are only important insofar as they affect model output? • Observations: • Constraints: • Task: • Decline to self-identify • Hispanic or Latino - A person of Cuban, Mexican, Puerto Rican, South or Central American, or other Spanish culture or origin regardless of race. • Hispanic or Latino • White (Not Hispanic or Latino) - A person having origins in any of the original peoples of Europe, the Middle East, or North Africa. • White • Black or African American (Not Hispanic or Latino) - A person having origins in any of the black racial groups of Africa. • Black or African American • Native Hawaiian or Other Pacific Islander (Not Hispanic or Latino) - A person having origins in any of the peoples of Hawaii, Guam, Samoa, or other Pacific Islands. • Native Hawaiian or Other Pacific Islander • Asian (Not Hispanic or Latino) - A person having origins in any of the original peoples of the Far East, Southeast Asia, or the Indian Subcontinent, including, for example, Cambodia, China, India, Japan, Korea, Malaysia, Pakistan, the Philippine Islands, Thailand, and Vietnam. • Asian • American Indian or Alaska Native (Not Hispanic or Latino) - A person having origins in any of the original peoples of North and South America (including Central America), and who maintain tribal affiliation or community attachment. • American Indian or Alaska Native • Two or More Races (Not Hispanic or Latino) - All persons who identify with more than one of the above five races. • Two or More Races • Hispanic or Latino • White (Not Hispanic or Latino) • Black or African American (Not Hispanic or Latino) • Native Hawaiian or Other Pacific Islander (Not Hispanic or Latino) • Asian (Not Hispanic or Latino) • American Indian or Alaska Native (Not Hispanic or Latino) • Two or More Races (Not Hispanic or Latino) • I identify as one or more of the classifications of protected veteran listed above • I am not a protected veteran
Apply in one click
Upload My Resume
Drop here or click to browse · Tap to choose · PDF, DOCX, DOC, RTF, TXT