Looks like you have JavaScript disabled. For the full Twine experience, you will need to re-enable it.

I'm Ashton Cothran, a Senior / Principal Applied AI & Machine Learning Engineer with 12+ years of experience building, deploying, and governing production ML systems that power financial decisions. I specialize in credit underwriting, fraud detection, pricing, and risk, delivering measurable business impact at scale while ensuring governance and regulatory readiness. I lead cross-functional teams in regulated fintech environments, translating statistical rigor into revenue growth, loss reduction, and responsible AI. I mentor engineers, design cloud-native, low-latency ML services, and champion guardrails, interpretability, and bias detection to support scalable, compliant AI.…I'm Ashton Cothran, a Senior / Principal Applied AI & Machine Learning Engineer with 12+ years of experience building, deploying, and governing production ML systems that power financial decisions. I specialize in credit underwriting, fraud detection, pricing, and risk, delivering measurable business impact at scale while ensuring governance and regulatory readiness. I lead cross-functional teams in regulated fintech environments, translating statistical rigor into revenue growth, loss reduction, and responsible AI. I mentor engineers, design cloud-native, low-latency ML services, and champion guardrails, interpretability, and bias detection to support scalable, compliant AI.

Ashton Cothran

Data Scientist, AI Engineer, AI Developer, +2





I'm Ashton Cothran, a Senior / Principal Applied AI & Machine Learning Engineer with 12+ years of experience building, deploying, and governing production ML systems that power financial decisions. I specialize in credit underwriting, fraud detection, pricing, and risk, delivering measurable business impact at scale while ensuring governance and regulatory readiness. I lead cross-functional teams in regulated fintech environments, translating statistical rigor into revenue growth, loss reduction, and responsible AI. I mentor engineers, design cloud-native, low-latency ML services, and champion guardrails, interpretability, and bias detection to support scalable, compliant AI.…I'm Ashton Cothran, a Senior / Principal Applied AI & Machine Learning Engineer with 12+ years of experience building, deploying, and governing production ML systems that power financial decisions. I specialize in credit underwriting, fraud detection, pricing, and risk, delivering measurable business impact at scale while ensuring governance and regulatory readiness. I lead cross-functional teams in regulated fintech environments, translating statistical rigor into revenue growth, loss reduction, and responsible AI. I mentor engineers, design cloud-native, low-latency ML services, and champion guardrails, interpretability, and bias detection to support scalable, compliant AI.

Available to hire

I’m Ashton Cothran, a Senior / Principal Applied AI & Machine Learning Engineer with 12+ years of experience building, deploying, and governing production ML systems that power financial decisions. I specialize in credit underwriting, fraud detection, pricing, and risk, delivering measurable business impact at scale while ensuring governance and regulatory readiness.

I lead cross-functional teams in regulated fintech environments, translating statistical rigor into revenue growth, loss reduction, and responsible AI. I mentor engineers, design cloud-native, low-latency ML services, and champion guardrails, interpretability, and bias detection to support scalable, compliant AI.

Skills

Experience Level

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Intermediate

Work Experience

Ramp Principal Applied AI & ML Engineer at Ramp

January 1, 2022 - Present

Owned business-critical ML models across credit decision, fraud detection, and financial intelligence. Designed and deployed explainable ML models that improved fraud detection precision by 18–25%, reduced false positives while maintaining regulatory compliance. Led offline experimentation and error analysis that drove 12–15% improvement in approval quality without increasing portfolio risk. Implemented model monitoring frameworks for drift, stability, and bias, reducing post-deployment incidents by 30%+. Spearheaded engineers to deploy models into low-latency cloud-native systems, enabling real-time resolution at sub-100ms latency. Initiated LLM-driven analytics and agentic workflows (RAG, embeddings) that reduced internal analysis turnaround time by 40–50%.

Applied ML Lead at Capital One

January 1, 2019 - January 1, 2022

Crafted and maintained credit underwriting and fraud detection models supporting 20M+ customer decisions per year. Developed feature engineering pipelines leveraging large-scale transactional data, increasing model AUC by 6–10% across use cases. Conducted population stability and drift analyses, enabling retraining and reducing model degradation incidents by 25%. Orchestrated batch and near-real-time inference pipelines, improving decision throughput by 3×. Collaborated with risk, compliance, and audit teams to support 6–8 internal and regulatory model examinations, achieving zero critical findings.

Senior Machine Learning Engineer at Stripe

January 1, 2016 - January 1, 2019

Developed ML models for fraud detection and transaction ranking, driving $8–12M in annual fraud loss reduction. Led feature engineering and experimentation efforts that improved fraud recall by 10–15% at constant false-positive rates. Executed A/B tests validating ML-driven improvements, resulting in 4% conversion uplift and sustained customer experience improvements. Partnered with engineers to transition ML models into scalable production services supporting 100M+ annual payment transactions across global payment flows.

Data Analyst (Scientist) at JPMorgan Chase & Co

January 1, 2013 - January 1, 2016

Delivered SQL- and Python-based analytics over TB-scale enterprise financial datasets, supporting risk reporting and evaluations for 10+ business units. Automated end-to-end analytics workflows, reducing manual reporting effort by 30–40% and improving data timeliness. Performed exploratory data analysis and hypothesis testing on 10+ high-impact risk initiatives per year, informing risk policy changes and operational decisions. Authored and maintained model documentation for 10+ production models, aligned with governance standards and supporting internal audit and regulatory reviews.