[Remote] ML Engineer (AI-Native Systems & Forecasting)

Note: The job is a remote job and is open to candidates in USA. Ando is building AI-native workforce infrastructure for hourly workers, focusing on creating accurate demand forecasts and optimizing labor allocation. The ML Engineer will design, develop, and deploy machine learning systems, impacting real-world outcomes through the full data and ML lifecycle.ResponsibilitiesDesign, build, and deploy production-grade ML systems for demand forecasting and labor optimizationOwn the full ML lifecycle, including data ingestion, feature engineering, model training, deployment, and monitoringInherit and remediate messy, inconsistent datasets and establish scalable data pipelinesArchitect data systems across ingestion, warehousing, transformation, and feature storesBuild and maintain LLM-native systems, including RAG pipelines, prompt systems, and evaluation frameworksMake pragmatic decisions on modeling approaches, including when to use APIs, fine-tuning, or custom modelsDesign and implement model evaluation systems that measure performance continuously, not just at launchImplement monitoring, drift detection, and feedback loops to improve model performance over timeDesign and run experiments, including A/B testing and statistical validation of model performanceTranslate model performance and tradeoffs into clear insights for product and business stakeholdersCollaborate closely with Product, Engineering, and Operations to integrate ML into core workflowsSkills5–10+ years of experience in machine learning, data science, or applied AI rolesProven experience shipping ML systems into production environmentsStrong experience working with real-world, imperfect datasets in mid-maturity or scaling organizationsDeep understanding of the full data stack, including ingestion, warehousing, feature engineering, and model servingExperience designing and operating ML pipelines and workflows in productionHands-on experience with LLM systems, including RAG, prompt design, and evaluation frameworksStrong foundation in statistics, experimentation, and model evaluationExperience with monitoring, observability, and model performance tracking over timeAbility to operate with high ownership, ambiguity, and minimal process overheadStrong communication skills, with the ability to translate technical decisions into business impactExperience with time-series forecasting, demand modeling, or optimization systemsExperience building or integrating with labor, logistics, or marketplace systemsFamiliarity with modern ML infrastructure (Airflow, dbt, feature stores, etc.)Experience fine-tuning or training custom modelsExperience hiring or mentoring ML or data team membersCompany OverviewAI-native workforce infrastructure for predictive demand and intelligent workforce allocation. It was founded in 2024, and is headquartered in San Francisco, California, USA, with a workforce of 11-50 employees. Its website is https://ando.work.