Lead Data Scientist

Lead Data Scientist (Ranking & Recommendation Systems)

Remote (US Only)

$200,000 – $220,000 Base + Bonus

Are you ready to take ownership of upstream modeling efforts at a mission-driven organization focused on intelligent prioritization and large-scale decision systems? We're looking for an exceptional Lead Data Scientist to shape core retrieval and ranking infrastructure that drives real impact.

Why This Opportunity?

High-Leverage Retrieval & Ranking Work

• Design algorithms that surface the most relevant actions, claims, or data in complex operational workflows.
• Tackle core challenges in entity ranking, recommendation, and prioritization using structured and semi-structured data.
• Drive offline evaluation, experiment design, and principled iteration using business- and model-facing metrics.

A Focused, Highly Technical Team

• Join a small, fast-moving group of scientists and engineers with deep experience in optimization, ML systems, and large-scale modeling.
• Work in a culture that values clean modeling, strong architecture, and scientific rigor — not just Jupyter notebooks.
• Collaborate closely with product and engineering to turn modeling insights into production-grade solutions.

Remote-First, No Bureaucracy

• Fully remote (U.S.-based candidates only), with flexible hours and an emphasis on deep, focused work.
• Lean teams, minimal overhead, and strong execution culture — a place for people who like to build and move fast.

What the Role Involves

• Develop ranking and retrieval systems from first principles using optimization, probabilistic modeling, and hybrid recommenders.
• Lead the full lifecycle of model development — from objective definition and data exploration to deployment and post-launch evaluation.
• Analyze large-scale behavioral and transactional data to inform model design and uncover latent patterns.
• Own offline experimentation frameworks, design A/B tests, and contribute to a metrics-driven culture of iteration.
• Mentor junior team members and help set standards for experimentation, reproducibility, and performance.

What We're Looking For

• 6+ years of experience in data science, machine learning, or optimization, ideally with ownership of ranking/recommendation systems.
• Expertise in collaborative filtering, entity ranking, or personalized retrieval pipelines.
• Strong foundation in numerical optimization, statistical modeling, and ML evaluation techniques.
• Production-level coding experience in Python and proficiency with frameworks like PyTorch, TensorFlow, or XGBoost.
• Experience with data tooling and pipelines (e.g., Spark, Airflow), and a solid grasp of system performance tradeoffs.
• Ability to translate ambiguous, high-level problems into measurable, testable solutions — and then execute.

This is a rare opportunity to lead upstream modeling in a production environment, working on high-impact systems that blend precision science with real-world complexity. If you're energized by retrieval, ranking, and recommender systems — and you want your models to matter — we’d love to hear from you.