Staff Machine Learning Engineer

About the role

Every workout iFIT recommends is a small promise: that we know what a member is training for, and what they are ready for next. Keeping that promise across millions of members and every surface in the product is the job.

We are hiring a Staff ML Engineer to own recommendations and search end to end, from strategy through production. You will shape how personalization works here rather than implement someone else's spec.

What you will own

• The recommendation and search strategy across product surfaces: the approach, what gets prioritized, and the decisions that follow from results
• End-to-end ML systems for ranking, retrieval and personalization, covering data pipelines, feature design, training, evaluation and serving
• An experimentation loop rigorous enough that relevance work turns into measured member impact
• Reliability and safe iteration as the system grows, working closely with Data and Security
• The long-term health of what you build. Projects here are not handed off to a maintenance team

What we are looking for

• Recommendation or search systems you have taken to production and owned, not research prototypes
• Strong ML engineering fundamentals across ranking and retrieval: feature engineering, model training, evaluation, and the practical realities of deployment
• A track record of connecting model changes to product outcomes, through experiments that informed real decisions
• Solid software engineering: reliable services and pipelines, maintainable code, and comfort debugging systems you did not write
• Clear communication with product and engineering partners about trade-offs and progress
• Proficiency with Claude Code as a daily working tool

Even better if you have

• Large-scale personalization experience across multiple surfaces, high traffic, and catalogs that change constantly
• Worked with LLMs in retrieval or ranking, or built AI-native development workflows

How we work

Roughly 95% of the code in our platform org is AI-generated. That has genuinely changed what engineering looks like here. We review plans before code. We build harnesses and quality gates instead of reading every diff. We invest in the workflows that make the next feature faster, and we expect engineers to own what they ship regardless of what wrote the first draft.

If you already work this way, you will feel at home immediately. If you want to, this is a good place to learn it properly.

Your first 90 days

• Build an end-to-end picture of how personalization and search data flows, where the key metrics live, and what the current system is actually optimizing for
• Identify the highest-leverage relevance opportunities and propose an experimentation plan with clear decision criteria
• Ship at least one meaningful production improvement and communicate what it moved
• Put guardrails around reliability and data constraints so the system can keep iterating safely

Compensation

$175,000 to $220,000 base salary, plus a 15% target bonus. Fully remote within the United States.

A note on backgrounds

If you have built and scaled recommendation or search systems anywhere, whether at a startup, a large company, or in open source, we would like to hear from you, whether or not your title has said "Staff" before.