Machine Learning Specialist – Price Prediction
About Us
Cherry is a fast-growing market place for buying, selling, leasing, and auctioning commercial vehicles and equipment. We’re building an industry-first valuation engine that helps our users make informed decisions in seconds. Now, we’re looking for a Machine Learning Engineer who can bring strong expertise in predictive modeling, and ideally document automation using AI.
Role Overview
We are seeking an experienced ML specialist to build models that predict market prices for trucks and equipment based on auction results, historical sales, and vehicle specifications. This role will also involve setting up automated data pipelines, scraping structured and semi-structured data, and optionally working on generating intelligent reports or documents from data.
Key Responsibilities
- Build and refine price prediction models using data from auction sites, dealership listings, and historical records.
- Design and maintain data scraping pipelines will be a plus (e.g., BeautifulSoup, Selenium, Scrapy) to gather auction and sale data from multiple public sources.
- Clean, normalize, and store data efficiently for training and inference.
- Apply feature engineering techniques on specs like make, model, mileage, year, VIN, etc.
- Work closely with product and engineering teams to deploy models in production.
- (Optional but valued): Use NLP or generative AI to create documents or listing descriptions automatically.
Requirements
- Proven experience in machine learning with a focus on regression/predictive models.
- Strong Python skills; familiar with tools like Scikit-learn, XGBoost, LightGBM, TensorFlow, or PyTorch.
- Experience in web scraping is a plus (BeautifulSoup, Scrapy, etc.).
- Familiarity with model evaluation metrics for regression (e.g., RMSE, MAE).
- Comfortable working with structured data (CSV, JSON, APIs) and preprocessing pipelines.
- Fluent in Git and version control workflows.
- Experience deploying or working with models in production (FastAPI, Flask, AWS/GCP preferred).
Nice to Have
Familiarity with automated document generation, AI agents, or LLM APIs (OpenAI, Langchain).