Job Description
Lead Data Scientist - Collections & Operations
\n
US (Remote)
\n
Up to $200,000
\n
\n
I'm partnered with a well-funded consumer lending fintech looking for a Principal Data Scientist to become the technical lead for a highly visible machine learning function focused on customer operations and collections strategy.
\n
\n
This isn't a people management role disguised as a technical one.
\n
\n
You'll be the person setting the modelling standard, driving the roadmap day-to-day, and acting as the technical point of reference for internal Data Scientists, external consultants and specialist contractors.
\n
\n
Why this role is interesting
\n
Most collections organisations have spent years optimising what action to take.
\n
\n
Far fewer have solved how different customers respond to different interventions.
\n
\n
Some engage immediately via SMS. Others respond to email campaigns. Others require a completely different approach.
\n
\n
Understanding those behavioural signals and translating them into production-grade decisioning models remains a surprisingly open problem and one of the core challenges this team is tackling.
\n
You'd be joining at a point where the organisation has meaningful scale, strong funding and large volumes of customer interaction data, but where the collections data science capability is still evolving.
\n
\n
For the right person, there's genuine opportunity to shape what the function looks like over the next several years.
\n
\n
What you'll be responsible for
\n
- \n
- Driving execution of the collections data science roadmap
- Acting as the lead technical authority across modelling initiatives
- Building ML models that predict customer response, engagement and repayment behaviours
- Influencing how and when customers are contacted across different channels
- Establishing scalable modelling and experimentation frameworks
- Raising engineering and production standards across the wider team
- Reducing reliance on external consultancies by building durable internal capabilities
\n
\n
\n
\n
\n
\n
\n
\n
\n
Tech Environment
\n
The team operates within a modern ML stack including:
\n
- \n
- Python
- Scikit-Learn
- LightGBM
- Airflow
- Kubernetes
- Google Cloud Platform
- MLflow
- BentoML
- Chalk Feature Store
- DVC
\n
\n
\n
\n
\n
\n
\n
\n
\n
\n
\n
\n
Strong interest in MLOps and production machine learning is viewed very positively.
\n
What they're looking for
\n
- \n
- 7+ years' commercial Data Science experience (or equivalent advanced academic background)
- Proven experience deploying and monitoring machine learning models in production
- Strong software engineering habits including testing, code review and reproducibility
- Experience leading technically complex projects and influencing senior stakeholders
- Comfortable operating as the most senior individual contributor on a workstream
- Experience within fintech, lending, risk, operations, marketing science or other large-scale predictive modelling environments
\n
\n
\n
\n
\n
\n
\n
\n
Previous collections experience would help but is not required.
\n
\n
Package
\n
💰 Up to $200,000 base
\n
📈 Bonus + Equity
\n
🏥 Full benefits package
\n
🏠 Fully Remote (US)