Data Scientist

About the company

Findigs is building a modern rental screening platform designed to make the leasing experience faster, clearer, and fairer for everyone involved. The company focuses on replacing slow, confusing screening workflows with an end-to-end system that gives both property managers and renters a more dependable experience.

Backed by $78M in funding from investors associated with well-known companies such as Affirm, Gusto, and Uber, Findigs is scaling quickly with a product and team centered on transparency, accuracy, and better decision-making. The company is working to expand its impact and is looking for people who want to help modernize a major industry.

Role overview

Findigs uses an AI underwriting engine called DecisionAssist to support or influence thousands of rental decisions each week. In this role, you will deepen the company’s applied machine learning and data science capabilities by owning model development work, experiment design, and analysis that affects both renters and property managers.

You will report to the Lead Analytics Engineer and operate in a technical, high-ownership environment. The role is designed for someone who enjoys building and improving production models, applying statistical rigor to product decisions, and expanding into broader strategic responsibilities as the team grows. You will work closely with Product and Engineering to turn rental risk and user behavior into models, experiments, and actionable insights.

Impact areas

• Lead feature engineering, model iteration, and evaluation for DecisionAssist across both operational serving work and analytics-driven modeling in Snowflake.
• Partner with Product and Engineering to identify the most meaningful signals and understand their influence on outcomes.
• Design, execute, and analyze experiments for underwriting changes as well as renter-facing and property-manager-facing product updates.
• Build and support predictive and risk models used in screening workflows, including delinquency risk, income estimation, and fraud-related signals.
• Write clean Python and work comfortably with dbt and a modern data stack, even though you will not own the warehouse or pipeline architecture.
• Investigate ad hoc business and product questions, such as approval-rate variation, cohort differences, and signal performance.

Required qualifications

• At least 4 years of practical experience in data science or applied machine learning, ideally in fintech, proptech, or another environment where decisions carry significant stakes.
• Strong programming ability in Python, including tools such as pandas, scikit-learn, and statsmodels or equivalent libraries.
• Proven ability to independently design, run, and interpret A/B tests.
• Advanced SQL capability and familiarity with a modern analytics stack such as dbt, Snowflake, or Sigma.
• Good understanding of supervised learning methods, including classification, regression, and tree-based models.
• Excellent written communication skills and the ability to explain modeling decisions and tradeoffs to non-technical stakeholders.
• Genuine interest in housing and credit-related data.
• Applicants must not require employer sponsorship for a U.S. work visa, as sponsorship is not available.

Preferred experience

• Experience building or contributing to credit, risk, or underwriting models in production.
• Awareness of fair lending and disparate impact considerations in machine learning.
• Experience working on systems where model outputs affect real people and require careful judgment.
• Ability to move between exploratory analysis and production-quality implementation without separate handoffs.
• Exposure to LLM work such as fine-tuning, retrieval, or integration, especially for underwriting or screening automation.
• Experience in a startup or scale-up environment.

Benefits and perks

• Hybrid work setup with 3 to 4 in-office days each week.
• Core collaboration days are Monday, Tuesday, and Thursday at the NoHo office.
• Mission-oriented culture focused on collaboration, learning, and meaningful impact.
• Competitive base salary plus pre-IPO equity.
• Unlimited paid time off and company-wide holidays.
• Health benefits.
• 401(k) match up to 4%.
• Monthly gym stipend.
• Lunch provided every day.

Interview process notes

The company may record interviews using Brighthire.ai so interviewers can stay focused on the conversation. Candidates can opt out of recording at any stage of the interview process.

Equal opportunity and hiring practices

Findigs considers all applicants based on merit and directly relevant professional skills. The company may use AI tools to assist with parts of recruiting, such as resume review, response analysis, and inconsistency checks, but final hiring decisions are made by people.

Compensation disclosure

For New York City pay transparency purposes, the company notes that actual compensation depends on factors such as skill set, years and depth of experience, and the scope of the role. Full-time employees also receive an equity compensation package in addition to cash compensation.