ML Researcher

Schemathics is a leader in AI-powered performance marketing, operating across 25+ verticals with unmatched precision, speed, and scale. Our proprietary technology stack integrates seamlessly with major media platforms, enabling real-time event-level data exchange, optimization, and attribution.

At the core of our operation is a deep commitment to AI-driven decision-making. From real-time bidding engines and predictive lead scoring to campaign automation and anomaly detection, our in-house AI models are central to how we scale campaigns, reduce inefficiencies, and outperform market benchmarks.

We’ve built and continue to evolve a robust internal platform to empower media buyers, analysts, and operators with real-time alerts, smart recommendations, and semi-autonomous optimization tools.

Role Summary

Develops, trains, and evaluates ML models - especially tabular, predictive, and ranking

models - and contributes directly to production-first modeling efforts across the funnel.

Minimum Requirements (Must Have)

● Strong hands-on experience with tabular ML models (XGBoost, LightGBM,

CatBoost, logistic regression, etc.)

● Proven experience with data wrangling, feature engineering, dataset preparation

● Experience training, tuning, and evaluating models at scale

● Solid understanding of model validation

● Strong Python skills and familiarity with ML libraries

● Ability to translate hypotheses into measurable experiments

● Experience working closely with data engineering pipelines

Preferred Qualifications (Nice to Have)

● Experience with inference engineering: packaging models, building inference

endpoints, optimizing latency

● Exposure to model monitoring: drift, data quality checks, performance monitoring

● Experience with containerization (Docker) and serving frameworks (FastAPI, Flask,

TorchServe, Bento, etc.)

● Experience deploying ML models in production environments

● Prior experience with ranking, scoring or optimization models