Senior Machine Learning Engineer

TL;DR

Senior Machine Learning Engineer (Ranking & Relevance): Build and iterate on ML models powering patient-provider matching from search and candidate generation to final ranking and personalization with an accent on leveraging patient signals, provider attributes, and outcomes data. Focus on end-to-end model lifecycle including offline evaluation, production deployment, monitoring, A/B experimentation, and cross-functional collaboration to improve matching quality.

Location: New York, NY; San Francisco, CA; Seattle, WA, United States

Salary: $218,500 - $273,125

Company

Series D mental healthcare platform automating insurance admin, serving 70k+ providers across all 50 US states and 1M+ patients.

What you will do

• Build and iterate ML models for matching, ranking, search, discovery, and personalization to connect patients with right providers.
• Leverage patient signals, provider attributes, and outcomes to enhance matching accuracy over time.
• Own full model lifecycle: offline evaluation, experimentation, production deployment, and monitoring.
• Design and analyze A/B tests, define metrics, and translate results into product decisions.
• Collaborate with product, engineering, and data science teams to scope problems and ship impactful improvements.
• Contribute to team ML best practices via code reviews, documentation, and knowledge sharing.

Requirements

• 5+ years in applied ML, 3+ years hands-on in ranking, relevance, recommendations, search, or personalization.
• Fluent in Python; experienced with TensorFlow, PyTorch, Scikit-learn, or CatBoost.
• Experience taking models from prototype to production at scale.
• Skilled in designing/running A/B experiments, metrics selection, and result interpretation.
• Product intuition to improve patient experience beyond offline metrics.
• Strong collaboration and communication in cross-functional environments.

Nice to have

• Experience with search, discovery, matching, or consumer personalization systems.
• Familiarity with vector search, embeddings, semantic search.
• ML infrastructure: feature stores, model monitoring, retraining pipelines.
• Metaflow, SageMaker, Outerbounds.
• Background in healthcare, marketplace, or B2C user-provider matching.

Culture & Benefits

• Equity compensation, medical/dental/vision, HSA/FSA, 401K.
• Work-from-home stipend, therapy reimbursement, 16-week parental leave, Carrot Fertility.
• 13 paid holidays + Holiday Break, flexible PTO, EAP, training/professional development.

Hiring process

• Initial screen with recruiting.
• First round: live coding with engineer.
• Final rounds: technical and non-technical interviews with team.
• References and offer with equity details.