Senior Machine Learning Engineer

ClarityPay•New York City, NY

About The Position

We give businesses and their customers peace of mind by solving complex credit challenges with precision, speed, and intelligence, combining deep expertise with advanced technology, to simplify the experience and deliver better outcomes, every time. We're a fast-growing fintech empowering enterprise merchants with smarter, more adaptive pay-over-time solutions. From point-of-sale financing to “Buy Now, Pay Later” programs and loyalty integrated offers, we’re building configurable credit tools that help businesses serve more of their customers. We value teamwork, clarity of purpose, and rigorous attention to data to drive action. We balance speed and excellence to deliver an exceptional customer experience. Role Overview: ClarityPay is undertaking transformative investments in machine learning products, algorithms, and platforms. We are building a team of technically proficient, hands-on engineers who are passionate about solving complex optimization problems across customer complaints, collections, and offer optimization. This role is for the engineer who looks at a "collections process" and sees a Reinforcement Learning environment . You will engage directly with the problem space—performing deep case reviews to understand the "why" and "what"—and develop rigorous hypotheses to optimize outcomes. You will move beyond simple predictive models to build transformative algorithmic solutions using Bayesian Black Box optimization, Contextual Bandits, and Deep Q-Networks (DQN/DDQN). The problem space here is ripe for innovation. Your curiosity, drive, and aptitude will determine the ceiling of your impact. You will have the opportunity to expand into leadership responsibilities, including technical mentorship and management of offshore engineering teams.

Requirements

1-5+ years of industry machine learning experience with excellent engineering skills.
Strong theoretical understanding and practical experience with Reinforcement Learning (RL), Bandit algorithms (Thompson Sampling, UCB), and Bayesian inference. You know when to use a simple regression and when to deploy a DDQN.
Expertise in Python and familiarity with ML frameworks such as TensorFlow, PyTorch, Boosted Trees, and Scikit-Learn. Experience with SQL and data manipulation is required.
Experience with ML cloud platforms such as AWS Sagemaker, Databricks, or similar. You are comfortable building your own deployment pipelines.
You have a strong background in experiment design, A/B testing, and causal inference. You understand that a model is only as good as the experiment that validates it.
You are willing to look at "messy" operational data (complaints, collections logs) and find the mathematical structure within it.

Responsibilities

End-to-End Problem Solving: Own the full lifecycle of the solution. You will dive deep into case reviews to formulate hypotheses, design rigorous A/B tests to validate them, and automate the scaling of successful strategies.
Advanced Algorithmic Development: Develop and deploy inferential solutions that optimize management levers. You will implement and tune advanced techniques including Contextual Bandits, Deep Q-Networks (DQN), Double DQN, and Bayesian optimization to infer causal effects and maximize long-term reward.
Engineering & Reliability: Build the "pipes" and the "brains." You will create robust data pipelines, develop inferential models, and ensure solution reliability in production. You will champion scientific rigor in data-driven decision-making.
Continuous Optimization: Continuously optimize the quality of our machine learning models for incremental lift estimation and causal inference, ensuring we are making the most efficient use of resources.
Technical Leadership: As a senior member of the team, you will help define our engineering standards, evaluate and adopt new technologies, and provide technical leadership/management to offshore development teams to scale our delivery velocity.