Data Scientist

About the role

Brivity is a profitable, high-growth company operating at the intersection of real estate and technology. We are looking for an independent data scientist to join our small team to build and deploy machine learning models and reasoning systems.

Key facts

What you'll do

• Test hypotheses using data and maintain intellectual honesty in your findings.
• Build and validate models ranging from gradient boosting to transformer architectures.
• Manage the full lifecycle of models, including production deployment and ongoing maintenance.
• Document testing protocols, model decisions, and evaluation results.
• Monitor production performance to determine when retraining or architectural changes are necessary.
• Research agentic and reasoning systems to identify practical applications for our product.

Requirements

• Bachelor degree or equivalent professional experience.
• 3+ years of relevant work experience.
• 3-5+ years of hands-on AI experience, including LLM work and production-level ML/DL model deployment.
• Proficient in Python, SQL, and Snowflake.
• Familiarity with AWS services such as Bedrock, SageMaker, Lambda, S3, EC2, Step Functions, CloudWatch, and EKS.
• Experience with Docker and infrastructure-as-code.
• Knowledge of supervised and unsupervised learning, deep learning, and reinforcement learning.
• Experience with PyTorch, TensorFlow, scikit-learn, XGBoost, LightGBM, AutoGluon, and CatBoost.
• Familiarity with experiment tracking tools like MLflow or Weights & Biases.
• Experience with Git, Jira, Confluence, Slack, and Jupyter.

Nice to have

• Experience with agent frameworks like LangChain or reasoning architectures like ReAct and chain-of-thought.
• Background in planning algorithms or decision-making under uncertainty.
• Skills in image classification, object detection, segmentation, or transfer learning.
• Domain knowledge in real estate, mortgage, financial services, or logistics.
• Experience with time series forecasting or geospatial analysis.
• Knowledge of CI/CD for ML, A/B testing, and model drift monitoring.

Skills & tools

• Python, SQL, Snowflake, AWS (Bedrock, SageMaker, Lambda, S3, EC2, Step Functions, CloudWatch, EKS), Docker, PyTorch, TensorFlow, scikit-learn, XGBoost, LightGBM, AutoGluon, CatBoost, MLflow, Weights & Biases, Git, Jira, Confluence, Jupyter.

Practical notes

• Benefits include comprehensive insurance, 401(k) match, stock options, a stock purchase plan, and flexible PTO.
• This role allows for remote work from your preferred location.