Full Job Description
We9re looking for a Senior Data Scientist to join Arcadia9s Applied AI team - a small, delivery-focused group within R&D that ships the machine learning and AI systems powering Arcadia9s utility data platform. This is a hands-on role standing up new ML / AI capabilities across our core workstreams: utility bill data extraction, forecasting, and audit/anomaly detection. You9ll work closely with engineering partners and the Director of Applied AI, with the experience to own ambiguous problems end to end, set the technical approach where none exists yet, and help shape how the team sequences its work.
What you will do:
Own delivery of one or more core workstreams - bill data extraction, forecasting, or audit/anomaly detection - and flex across them with your manager as priorities shift.
Build, evaluate, and improve production models: document classifiers and extraction agents, forecasting models for bill availability and spend, and detection and tuning for audits and controls.
Set the technical approach on problems where the right method isn9t established - investigate, decide, and carry the recommendation through to a shipped result.
Partner with the Director on prioritization and sequencing across workstreams, bringing a point of view on where the team should invest rather than only the capacity to execute.
Write production-grade Python and contribute to the shared codebase, pipelines, and design docs - this is a live production system, not a notebook sandbox.
Partner with engineering on model integration, monitoring, and post-deployment behavior - as the authority on the modeling approach and the team9s resource for applying AI in production.
Automate manual steps in your own and the team9s workflow with AI tooling, and share the techniques that raise throughput.
What will help you succeed:
Substantial hands-on experience building and evaluating production ML models, with the judgment to make progress on ambiguous problems independently. The right person will need at least 3 years of experience working in ML models.
Strong ML fundamentals - statistics, classification, regression, and evaluation methodology.
Fluency in Python (pandas, scikit-learn, numpy) and SQL, and comfort working in a live production codebase not just notebooks.
Practical experience with LLMs or agentic workflows in production.
Comfort with imperfect ground truth and managing inherent uncertainty in data.
A track record of driving work with minimal oversight: forming and documenting assumptions, making the call on approach, and standing behind a recommendation.
Clear communication that adapts to the audience: able to explain model behavior to engineers and non-technical partners and make the case for a decision.
Bachelor9s or Master9s in CS, Statistics, Math, or a related field (or equivalent experience), plus a portfolio of past work - GitHub, papers, or project write-ups.
Benefits:
"Remote first" culture: work anywhere in the continental US as long as you have a reliable internet connection.
Flexible PTO: no accrued hours and no limit on the number of vacation days exempt employees can take each year.
11 annual holidays
10 days sick leave
Up to 2 weeks bereavement leave
2 volunteer days off
2 professional development days off
Parental leave benefits for all parents
75-95% employer cost coverage for medical, dental, and vision benefits for employees and dependents
Visa Sponsorship
Select R&D & Data roles: We are proud to offer visa sponsorship opportunities for qualified candidates interested in joining our team.
Other roles: Please note that we are unable to offer visa sponsorship for this position at this time.