Applied ML Engineer — Recommendation Systems

OceanAI

Remote · $120K – $145K · Full-time · Posted 6 months ago

This role is no longer accepting applications

Don't miss the next role like this

Create a free profile with your skills. We match you to new AI roles as they open, and companies hiring can contact you directly.

Create free profile, 2 minutes

Similar open roles you can apply to now:

See all open AI jobs

This role is no longer accepting applications

Don't miss the next role like this

Create a free profile with your skills. We match you to new AI roles as they open, and companies hiring can contact you directly.

Create free profile, 2 minutes

Similar open roles you can apply to now:

See all open AI jobs

About the role

A lot of recommendation work assumes huge catalogs and huge interaction volumes. We do not have either, at least not in the way the big entertainment platforms do. Our challenge is helping the right viewer discover the right factual content when data is sparser and user intent is more specific. We want someone who can improve ranking and discovery without reducing the product to click optimization. Editorial judgment matters here, and the engineer joining this team needs to be comfortable with that.

Fully remote.

Responsibilities

Improve personalised ranking and session continuation recommendations across web and TV clients
Design experiments that balance engagement gains with content diversity and editorial quality goals
Build features from watch behaviour, content metadata, and topic relationships
Partner with product and editorial teams on recommendation quality review loops
Contribute to monitoring and rollback practices for ranking model deployments

Requirements

4+ years of ML engineering in recommendation, ranking, search, or personalisation systems
Python for production and experimentation code
PyTorch for training representation or sequence models
SQL for feature analysis and recommendation investigation
Pandas for exploratory work and dataset construction
Statistics for experiment design and ranking evaluation