Overview In this role you design, build, and deploy ML/AI models for a decision intelligence platform. You will tackle causal inference, time-series forecasting, anomaly detection, and LLM-based reasoning to drive measurable business impact. You work across research and production to deliver end-to-end solutions, with a focus on calibrated confidence and actionable insights for senior leaders. This is a chance to shape how interventions are evaluated and recommended at scale.
Compensation / Benefits- health insurance (medical, dental, vision)
- RSUs and sign-on compensation
- 401(k) matching
- paid time off
- parennial leave
- life insurance and wellbeing programs
Responsibilities- Develop causal inference and root-cause analysis models to decompose metric movements into actionable drivers
- Create dose-response and intervention impact models
- Build time-series forecasting and projection models under different scenarios
- Design multivariate anomaly detection and trend identification systems
- Maintain confidence calibration for recommendations
- Design experiments and causal methods to attribute outcomes to interventions
- Design LLM prompting architectures for executive-quality narratives and decision rationales
- Build evaluation frameworks for LLM outputs and detect degradation
- Develop RAG systems grounding outputs in operational data and knowledge
- Own models end-to-end from research to production deployment and monitoring
- Plan and execute A/B tests and quasi-experiments to validate improvements
- Communicate complex results to non-technical, senior stakeholders
Key requirements- 3+ years of ML model development for business applications
- PhD in a quantitative field (or Master's + 4 years applied experience)
- Expertise in at least two: causal inference, time-series forecasting, anomaly detection, or NLP/LLMs
- Proficiency in Python and ML frameworks (PyTorch, TensorFlow, scikit-learn, statsmodels)
- Experience with experimental design and causal methods (DiD, synthetic control, IV, Bayesian causal inference)
- Experience deploying ML models to production
- Track record of publications or equivalent internal research contributions
- strong written and verbal communication
- ability to translate complex results for non-technical leaders
- cross-functional collaboration
- Python
- PyTorch
- TensorFlow
