Software Engineering - Lead Data Scientist

FICO

About The Position

FICO’s myFICO (Scores B2C) engineering team is seeking a Lead Data Scientist to build and operate machine learning and Generative AI solutions for consumer applications. This lead-level software engineering role develops data pipelines to prepare large datasets for modeling, builds and deploys production ML models with monitoring and retraining, and measures business impact through experimentation. The role also establishes ML engineering best practices for the team. The position partners with database engineering, product management, and InfoSec to deliver secure, compliant solutions that responsibly handle sensitive consumer data. It includes technical leadership through design discussions, code reviews, and mentoring, as well as collaboration with product and marketing partners to communicate analytical results. The role uses AI coding assistants and agentic workflows to accelerate delivery while reviewing and refining their output.

Requirements

Bachelor’s or Master’s degree in Computer Science, Data Science, Statistics, or a related field.
Demonstrated experience in data science, machine learning engineering, or applied AI, including models running in production.
Strong Python skills for data engineering and machine learning, including pandas, NumPy, scikit-learn, and PySpark, and comfort working in Jupyter notebooks.
Experience building data pipelines and processing large datasets with Spark, Redshift, or similar technologies.
Expert SQL skills for complex queries on large datasets.
Hands-on experience with ML frameworks such as XGBoost, TensorFlow, or PyTorch.
Experience operationalizing ML models, including deployment, monitoring, retraining, and CI/CD using SageMaker, MLflow, Docker, or similar tools.
Experience running data and ML workloads in AWS, such as S3, Glue, Lambda, or Bedrock.
Experience with LLMs such as Claude or OpenAI GPT, including prompt design, evaluation, and production deployment of Generative AI solutions.
Strong grounding in statistics, experimental design, and hypothesis testing.
Production ownership experience, including code review, release management, and mentoring.
Ability to explain technical results to non-technical partners.

Nice To Haves

Experience with RAG workflows.
Experience with vector stores.
Experience with MCP server integrations.
Experience with LLM fine-tuning.
Experience with workflow orchestration tools such as Airflow or Step Functions.
Experience with regulated consumer data, such as credit and financial services.

Responsibilities

Build and maintain Python data pipelines to ingest, clean, and transform large datasets into reliable, analysis-ready data and ML features.
Profile and validate data and implement quality checks for trustworthy models and analyses.
Develop machine learning models, including propensity, churn, segmentation, and forecasting models, from problem framing through evaluation.
Deploy models to AWS for batch and real-time scoring; monitor performance and drift; and automate retraining.
Design, evaluate, and improve LLM prompts and integrate Generative AI capabilities into existing applications.
Design and analyze A/B tests to measure business impact and explain results to product and marketing partners.
Lead design discussions and code reviews, mentor engineers and analysts, and establish ML engineering best practices.
Collaborate with database engineering, product management, and InfoSec to build secure, compliant solutions for sensitive consumer data.
Use AI coding assistants and agentic workflows, such as Claude Code, Cursor, and GitHub Copilot, while reviewing and refining their output.