Machine Learning Engineer

As a Machine Learning Engineer at withco, your primary responsibilities will include designing and developing data models that support our AI features, implementing analyses and models using first and third-party real estate data, and building a recommendation engine that simplifies the real estate decision-making process for small business owners.

To be a successful Machine Learning Engineer at withco, you should have a strong background in machine learning tools, data modeling, and experience with various ML techniques such as logistic regression and neural networks. Additionally, a passion for data and the ability to transform diverse datasets into actionable strategies is essential.

The culture at withco is highly collaborative and values accountability and clarity. As a Machine Learning Engineer, you'll be surrounded by a team of craftspeople, scientists, and former founders who thrive on curiosity and a desire to build impactful solutions for small businesses.

A great candidate for the Machine Learning Engineer role at withco is someone who is data-driven, technically brilliant, and possesses a deep understanding of machine learning practices. If you enjoy tackling complex problems and finding innovative ways to leverage data in support of small businesses, you’ll find yourself at home here.

Withco offers an attractive benefits package for Machine Learning Engineers, including top decile compensation, 100% company-paid medical, dental, and vision insurance, unlimited PTO, and eligibility for carried interest in our real estate vehicles, among other benefits aimed at creating an impactful career experience.

When answering this question, focus on your role in the project, the problem you aimed to solve, the tools you used, and the impact your solution had. Be concise but detailed enough to demonstrate your technical abilities and why it was successful.

Discuss the importance of problem understanding, data characteristics, and the scale of the problem. Explain your decision-making process for selecting between models such as logistic regression, decision trees, or neural networks based on performance and application needs.

Highlight techniques you use for data cleaning, normalization, and transformation. Explain how these processes help improve the performance of the models you develop, providing specific examples from past experiences.

Share insights from projects involving recommendation systems, detailing the algorithms you used and how you handled datasets. Discuss how you optimized the systems for better user engagement and accuracy.

Explain strategies such as cross-validation, regularization techniques, or pruning to mitigate overfitting. Illustrate with examples where applicable to show your depth of understanding in maintaining model performance.

Talk about different metrics based on the model type, such as accuracy, precision, recall, F1 score, or ROC-AUC. Make sure to connect these metrics back to the context of small business solutions at withco for relevance.

Discuss attending conferences, participating in online courses, or contributing to open-source projects. Show your commitment to continuous learning and how it would positively affect your role at withco.

Explain the significance of creating new input features to improve model performance and results. Provide examples of how specific features enhanced your data model outcomes in previous work.

Detail your systematic approach including testing component parts of the model, analyzing data flows, and ensuring data integrity to uncover issues. Illustrate with a past experience if possible.

Emphasize the collaborative nature of machine learning projects, discussing how working with data engineers, domain experts, and UX designers leads to better outcomes. Give an example of a successful collaboration in your experience.