Senior Applied Machine Learning Engineer

DAVID ESTALILLA

Senior Applied Machine Learning Engineer

******************@*******.*** 904-***-**** Jacksonville, FL SUMMARY

Senior Applied Machine Learning Engineer with 13 years of experience developing production-grade machine learning systems, behavioral analytics platforms, and AI-driven security solutions across cybersecurity and enterprise software environments. Strong expertise in Python, PyTorch, TensorFlow, scikit-learn, Machine Learning, Deep Learning, Behavioral Analytics, Threat Detection, Identity Security, Security Analytics, Real-Time Streaming Pipelines, MLOps, and cloud-native software engineering. Experienced developing anomaly detection systems, adaptive risk scoring platforms, telemetry analytics pipelines, and AI-driven security applications supporting authentication monitoring, session analytics, and adaptive access enforcement. Proven ability to collaborate with distributed engineering and security teams, translate complex operational and security problems into practical AI solutions, and deliver reliable production-ready systems in fast-paced environments.

EDUCATION

Bachelor’s Degree in Computer Science

University of Florida Gainesville, FL 2009 - 2013 EXPERIENCE

Senior AI/Machine Learning Engineer

Appgate Coral Gables, FL Oct 2024 – Present

• Developed production-grade machine learning threat detection systems using Python, PyTorch, Docker, Kubernetes, and cloud-native infrastructure supporting enterprise ZTNA and identity security environments.

• Built behavioral analytics and anomaly detection pipelines using Isolation Forest and Autoencoder models to identify suspicious authentication patterns, impossible travel events, privilege escalation activity, and abnormal session behavior.

• Developed real-time streaming pipelines using Kafka, PySpark, and event-processing services to analyze high-volume audit logs, identity telemetry, device activity, and session events in near real time.

• Designed and maintained dynamic risk scoring and signal aggregation systems that correlated detection events across users, devices, sessions, and network activity to support adaptive access enforcement decisions.

• Operationalized scalable MLOps workflows covering feature engineering, experiment tracking, model deployment, automated retraining, monitoring, and drift detection using MLflow, CI/CD pipelines, and Kubernetes.

• Implemented backend APIs supporting high-throughput security analytics applications and telemetry- driven inference services.

• Improved event ingestion and analytics performance through optimized preprocessing services and distributed event-processing pipelines for large-scale security event analysis.

• Tuned detection thresholds, validated behavioral signals, and refined anomaly scoring workflows to reduce alert fatigue and improve detection consistency.

• Partnered with security engineering, platform engineering, and product teams to align detection coverage, telemetry analysis, and operational requirements across enterprise customer environments.

• Supported technical design reviews, mentoring initiatives, code reviews, and software quality improvements within distributed engineering teams operating across US time zones. Senior AI/Machine Learning Engineer

Banyan Security Boston, MA Sep 2021 – Sep 2024

• Developed production-oriented machine learning and deep learning solutions using Python, TensorFlow, scikit-learn, and SQL to support enterprise security analytics and behavioral monitoring platforms.

• Built scalable analytics pipelines capable of processing authentication events, network telemetry, access logs, and session activity for behavioral anomaly analysis and threat signal generation.

• Maintained end-to-end ML pipelines for feature extraction, model training, deployment, validation, and operational monitoring across distributed security analytics environments.

• Applied classification, clustering, anomaly detection, and statistical modeling techniques to identify suspicious access behavior, insider activity indicators, and operational security anomalies.

• Expanded streaming analytics capabilities using PySpark, Spark Streaming, and distributed processing systems supporting near-real-time event analysis and telemetry enrichment.

• Integrated machine learning outputs into internal detection services and operational dashboards through scalable backend APIs and automated processing workflows.

• Contributed to implementation of scalable MLOps practices involving deployment automation, experiment tracking, retraining workflows, model validation, and operational monitoring processes.

• Improved detection quality through signal validation initiatives, false positive reduction efforts, and refinement of behavioral scoring workflows.

• Collaborated closely with engineering, analytics, and product teams to translate customer security requirements into scalable AI and software engineering solutions.

• Supported cloud-native deployment workflows using Docker, Kubernetes, and automated CI/CD processes across distributed production environments. Sr. Data Scientist/Machine Learning Engineer

Availity Jacksonville, FL May 2016 – Jun 2021

• Developed scalable data engineering and analytical processing workflows using Python, SQL, and enterprise reporting technologies supporting operational analytics and platform intelligence initiatives.

• Built recurring ETL pipelines, transformation services, and automated analytical processing systems supporting enterprise reporting and predictive analytics operations.

• Applied statistical analysis, exploratory data analysis, and predictive modeling techniques to operational and customer-related datasets across distributed healthcare systems.

• Optimized reusable SQL queries, aggregation services, joins, and validation routines supporting recurring analytical delivery and reporting consistency requirements.

• Worked with large datasets across PostgreSQL, MySQL, cloud storage platforms, and distributed processing environments to improve data accessibility and reporting reliability.

• Integrated analytical services, reporting workflows, and operational data systems into internal enterprise applications alongside backend engineering teams.

• Maintained monitoring scripts, validation workflows, and recurring pipeline automation processes to improve operational consistency and data quality management.

• Assisted with cloud migration initiatives, distributed processing improvements, and scalable reporting platform enhancements across engineering teams.

• Supported implementation of foundational machine learning workflows involving feature engineering, model evaluation, predictive analytics, and operational automation.

• Participated in technical planning discussions involving software engineering standards, reporting requirements, and cross-functional platform integration efforts. Data Scientist

Web.com Group Jacksonville, FL Nov 2013 – Apr 2016

• Built operational dashboards, analytical reports, and recurring reporting workflows using SQL, Python, and spreadsheet-based analysis techniques.

• Developed data cleansing, transformation, and validation workflows to improve reporting consistency and dataset quality across customer-facing platforms.

• Supported ETL workflows, database analysis tasks, and API-driven data extraction processes for internal analytics and operational reporting initiatives.

• Worked with PostgreSQL, MySQL, and SQL Server environments to consolidate, validate, and prepare datasets for recurring reporting and analytical workflows.

• Applied statistical analysis, trend analysis, and exploratory data profiling techniques to identify operational inconsistencies and reporting gaps.

• Automated recurring reporting requests through reusable SQL scripts, reporting templates, and standardized analytical workflows.

• Collaborated with engineering and analytics teams on reporting maintenance, data mapping, validation improvements, and operational support activities.

• Assisted with backend data integration workflows and reporting automation efforts supporting internal engineering and analytics operations.

• Participated in cross-functional discussions involving reporting requirements, data quality initiatives, operational analytics improvements, and platform support processes. SKILLS

Applied Machine Learning and Analytics:

Machine Learning, Artificial Intelligence, Deep Learning, Behavioral Analytics, Threat Detection, Anomaly Detection, Isolation Forest, One-Class SVM, Autoencoders, Predictive Modeling, Classification, Regression, Clustering, Feature Engineering, Model Evaluation, Statistical Modeling, Natural Language Processing, Risk Scoring Systems

Security Analytics and Detection Engineering:

Identity Security, User and Entity Behavior Analytics (UEBA), ZTNA, Audit Log Analysis, Authentication Analytics, Session Analytics, Network Telemetry Analysis, Behavioral Monitoring, Threat Signal Correlation, Security Analytics Pipelines, Adaptive Access Controls, Privilege Escalation Detection, Security Event Processing, Telemetry Enrichment, False Positive Reduction

Machine Learning Frameworks and Libraries:

Python, PyTorch, TensorFlow, scikit-learn, Pandas, NumPy, MLflow MLOps and Cloud Platforms:

MLOps, Model Deployment, Model Monitoring, Model Drift Detection, Experiment Tracking, CI/CD Pipelines, Docker, Kubernetes, Azure, Cloud-Native Deployment, Automated Retraining Data Engineering and Distributed Processing:

Data Engineering, ETL Pipelines, SQL, PostgreSQL, MySQL, PySpark, Apache Spark, Spark Streaming, Kafka, Distributed Data Processing, Streaming Pipelines, Data Validation, Data Ingestion Pipelines Software Engineering and Backend Development:

Software Engineering, REST APIs, Backend Development, API Integration, Distributed Systems, Microservices

Contact this candidate