Project Title: Python Developer Needed for Quantitative Research Engine (Data + Modeling System) Project Description: I am looking for an experienced Python developer with strong skills in data engineering, statistics, and quantitative modeling to build a production-quality research system. The project involves building a backend engine that ingests structured data from several APIs, stores it in a relational database, performs statistical modeling and probability estimation, and produces analytical outputs that can be used for research and decision-making. The system should be built like a professional quantitative research platform rather than a simple script. It will require automated data ingestion pipelines, normalization of multiple data sources, historical data storage, model evaluation, and a modular architecture that allows different statistical models to be tested and compared over time. The system will primarily operate as a command-line research tool rather than a web application or dashboard. Final Code Goal A key requirement is that the architecture supports multiple candidate models and a structured research workflow. The platform should be able to train and evaluate different modeling approaches on historical data, compare them using out-of-sample performance, and keep track of model versions and results. The goal is to build a framework that behaves like a “model research lab,” where different probability models can be evaluated, calibrated, and promoted based on performance rather than relying on a single fixed model. Training the Model Technically, the project will be implemented entirely in Python and should include a clean modular codebase, a PostgreSQL database schema, automated data ingestion modules, statistical modeling components, logging/auditability, and testing. The system should be designed for reproducibility and historical traceability so that results can always be reconstructed from the underlying data and model configuration. I am not looking for a lightweight prototype. The deliverable should be a well-structured, documented Python project that can run locally, ingest data, train models, evaluate them, and generate research outputs. The architecture should also be extensible so that additional models, datasets, or automation can be added later. Ideal Developer Background Strong Python backend engineering experience Experience with data pipelines and API integrations Experience with PostgreSQL and ORMs Background in statistics, machine learning, or quantitative modeling Familiarity with time-series or forecasting systems is a plus Deliverables Complete Python codebase Database schema and setup instructions Modular ingestion and modeling framework Documentation and tests Ability to run the system locally and reproduce results More detailed technical specifications will be provided after selecting a developer and signing an NDA.