Data Scientist

About the Company:

Cortex is an AI-powered platform built for real estate investors and asset managers. It transforms fragmented financial, technical, and commercial data into clear dashboards and predictive insights—helping real estate professionals optimize performance, reduce costs, and make smarter, faster decisions. Designed for strategic decision-making in real estate, Cortex uses advanced AI to make complex analysis and insights generation.

Responsibilities:

LLM/Generative AI Development

Design, implement, and optimize LLM-powered features leveraging GPT agents and advanced RAG architectures to deliver predictive insights and automated workflows.

Custom Model Development

Develop, train, and fine-tune novel machine learning and deep learning models from scratch using frameworks like PyTorch or TensorFlow, specifically targeting real estate performance optimization and risk assessment.

Data Engineering & Preparation

Own the end-to-end data pipeline, including sourcing, cleaning, transformation, and optimization of large, complex, structured, and unstructured real estate datasets for model consumption.

Research & Innovation

Conduct thorough research on state-of-the-art AI/ML methodologies (e.g., time-series forecasting, graph neural networks) and evaluate their applicability to real estate investment challenges.

Model Deployment & MLOps

Collaborate with MLOps and engineering teams to integrate trained models into production environments, ensuring scalability, low latency, and continuous performance monitoring.

Performance & Iteration

Define key performance indicators (KPIs) for AI features, monitor model performance post-deployment, and implement iterative improvements based on A/B testing and data drift analysis.

Requirements

• Strong Python programming expertise with a minimum of 3 years of hands-on experience developing production-grade AI/ML solutions.
• Deep, demonstrable experience with the practical application of GPT agents and LLM frameworks (e.g., LangChain, custom OpenAI API integrations) for complex task automation.
• Essential knowledge of advanced Retrieval-Augmented Generation (RAG) techniques, including vector indexing, chunking strategies, and proficiency with vector databases (e.g., Pinecone, Chroma).
• Expert proficiency in handling, querying (SQL), cleaning, transforming, and feature engineering large, multi-modal datasets.
• Proven experience in model lifecycle management, including training, validation, hyperparameter tuning, and fine-tuning custom models using PyTorch, TensorFlow, or similar deep learning frameworks.
• Familiarity with MLOps principles and tools for model versioning, deployment, inference optimization, and monitoring (e.g., MLflow, Kubeflow).
• Demonstrated capacity for independent, hypothesis-driven problem-solving and translating ambiguous business questions into rigorous data science projects.

Nice to Have

• Direct domain knowledge or experience with financial modeling, real estate analytics, or time-series data analysis.
• Experience building scalable data pipelines using tools like Spark, Kafka, or Airflow.
• Practical cloud deployment experience with AI services on platforms such as AWS (Sagemaker), GCP (Vertex AI), or Azure.
• Understanding of data governance, privacy, and security best practices specific to sensitive financial data.