[Hiring] Lead Machine Learning Engineer @The Shade Store

Role Description

The Shade Store is investing in machine learning to power the next era of our business: how we assign and manage customer leads, how we quote and sell custom products, and how we catch quality issues before they reach the workroom. The Lead ML Engineer sits on the Data & Analytics team and owns this capability end to end — the models, the features that feed them, and the services that serve them.

Know what you’re walking into: the data foundation for reliable ML doesn’t fully exist yet, and building it is part of the job. Our transactional systems carry legacy structures — missing relationships, integrity gaps, signals we don’t capture today. You’ll get into the weeds of our data, our application, and our organization: diagnose the gaps, specify the fixes, validate the results, then build and own the ML environment on top. This is a hands-on builder’s role for someone high-agency and pragmatic, fluent in both offline training and online serving, who wants to stand up a discipline rather than inherit one.

Responsibilities:

• Data Foundations
  • Database architectural experience; Experience architecting and building feature stores end-to-end.
  • Lead a diagnostic of our application databases to identify the legacy data issues blocking reliable ML — missing relationships, integrity gaps, uncaptured operational signals.
  • Specify the transactional data-model changes ML requires: you write the spec and acceptance criteria and validate the backfill; application engineering implements.
  • Own the bridge from operational (MySQL) to analytical (Snowflake) data, producing clean, trustworthy feature and training datasets on our dbt stack.
  • Build, deploy, and own the models that put prediction into the business. e.g., financial forecasts, MMM models, real-time routing and decisioning on inbound customer activity, propensity and risk scoring, and recommendation and ranking for a highly configurable product catalog.
  • Own the full lifecycle — feature engineering, offline training and validation, online serving, monitoring, drift detection, retraining.
  • Define model performance in business terms and hold models accountable to those measures after launch.
  • Serve models behind a documented internal service you own end to end — latency and availability guarantees, versioning, rollback, and the fallback contract the application relies on when a prediction is unavailable.
  • Establish reusable patterns and infrastructure (model registry, evaluation harness, monitoring, deployment path) so future use cases ship faster and safer, making pragmatic build-versus-buy calls along the way.
  • Serve as the senior technical anchor for ML, setting standards and de-risking ML in a live, business-critical environment.
  • Partner closely with Data, Analytics, and AI Engineering on shared evaluation standards, interface contracts, and joint design reviews.
  • Mentor engineers and deliver, as an early priority, an ML capability plan: what to develop internally, what to backfill, what to keep on contract.
  • Communicate fluently with technical and executive audiences, including the C-suite stakeholders sponsoring this investment.

Qualifications

• 5-10+ years of software and/or ML engineering experience, including significant time owning models in production after launch.
• 2-3+ years of productionizing ML/AI products.
• The full production ML path: feature engineering on operational data, offline training and validation, low-latency online inference, monitoring, and retraining.
• Strong Python for model development and strong SQL across operational and analytical data.
• Comfort at the application boundary — read a live transactional schema, write migration and backfill specs engineers can execute safely, and partner with them on APIs, data contracts, and shared operational ownership. MySQL preferred.
• Technical leadership without direct reports: setting standards, mentoring, raising the bar. Modern SDLC practices assumed (Git workflows, CI/CD, code review).
• Excellent communication; you translate fluently between deep technical detail and executive-level business impact.
• High agency and comfort with ambiguity. You don’t wait for a perfect environment — you diagnose, build, and improve it.

Requirements

• ML on a modern data stack (Snowflake, dbt, Dagster/Airflow, Fivetran), plus feature stores, model registries, or MLOps platforms.
• Working familiarity with LLM and applied-AI patterns (embeddings, RAG, evaluation).
• Experience in or alongside a legacy PHP/MySQL application, including safe schema migration and backfill strategy.
• Experience defining and measuring the business impact of a deployed model, not just its offline metrics.
• Background in e-commerce, retail operations, manufacturing, or DTC business models.
• Use of AI coding tools (Claude Code, Codex, Cursor), and prior experience standing up a new technical function inside a non-tech-native company.

Benefits

• Competitive salary
• Medical Benefits
• 401k with Company Match
• Up to $100k Life Insurance & Short-Term Disability (Employer Paid)
• Legal and Pet Insurance Plans
• Employee Assistance Program
• Product Discount