About the job
We are looking for an seasoned Applied Scientist to design, build, and deploy the ML/AI models that power our decision intelligence platform. You will work at the intersection of causal inference, time-series forecasting, anomaly detection, and LLM-based reasoning — all applied to real operational problems with measurable business impact.
Responsibilities
- Causal inference & root cause analysis: Build models that decompose fleet-wide metric movements into root causes, distinguishing correlation from causation across operational dimensions (site, service, failure mode, time)
- Dose-response modeling: Develop models that learn the quantitative relationship between intervention intensity and outcome magnitude
- Forecasting & projection: Build time-series models that project metric trajectories under different intervention scenarios, enabling "if we do X, expect Y by date Z" recommendations
- Anomaly detection & trend identification: Develop multi-variate anomaly detection that distinguishes signal from noise in noisy operational data, and identifies emerging patterns before they become crises
- Confidence calibration: Build and maintain calibrated confidence scores for recommendations, ensuring the system knows what it knows and what it doesn't
- Outcome attribution: Design experiments and causal methods to measure the true impact of interventions
- Structured reasoning: Design LLM prompting architectures that reliably transform operational data into executive-quality narrative summaries, decision framings, and recommendation rationales
- LLM evaluation: Build evaluation frameworks that measure LLM output quality (accuracy, actionability, calibration) and detect degradation over time
- RAG systems: Design retrieval-augmented generation systems that ground LLM outputs in operational data, historical playbooks, and institutional knowledge
- Progressive autonomy: Design the trust-calibration system where AI gradually earns expanded authority based on demonstrated accuracy over time
- End-to-end ownership: Take models from research through production deployment — you ship, you monitor, you iterate
- Experimentation: Design A/B tests and quasi-experiments to validate model improvements and measure business impact
- Stakeholder communication: Translate complex scientific results into actionable insights for non-technical senior leaders
Qualifications
Minimum
- 3+ years of building machine learning models for business application experience
- PhD in Machine Learning, Statistics, Computer Science, Operations Research, or related quantitative field (or Master's + 4 years of applied science experience)
- Strong expertise in at least two of: causal inference, time-series forecasting, anomaly detection, NLP/LLMs
- Proficiency in Python and ML frameworks (PyTorch, TensorFlow, scikit-learn, statsmodels)
- Experience with experimental design and causal methods (difference-in-differences, synthetic control, instrumental variables, or Bayesian causal inference)
- Experience deploying ML models to production (not just research/notebooks)
- Track record of publications or equivalent internal research contributions
Preferred
- Experience in building machine learning models for business application
- Experience with LLM integration (prompt engineering, RAG, fine-tuning, evaluation frameworks)
- Experience with dose-response modeling, treatment effect estimation, or pharmacometric-style modeling
- Experience with operational/infrastructure data (time-series at scale, noisy signals, multi-dimensional hierarchies)
- Experience with Bayesian methods (probabilistic programming, uncertainty quantification)
- Background in supply chain optimization, capacity planning, or operations research
- Experience building decision support systems that serve non-technical stakeholders
- Experience measuring GenAI/productivity tools' causal impact on workflows