Alessandro L.

Alessandro L.

Baltimore, United States
Hire Alessandro L. Hire Alessandro L. Hire Alessandro L.

About Me

Alessandro is a Machine Learning Engineer with over 10 years of experience in AI and data engineering, specializing in the entire product lifecycle from ideation to production. His key achievements include automating the training and deployment of TeleSign's multi-region risk scoring models (-70% delivery time) and optimizing FICO’s detection algorithms for credit card fraud (+5% accuracy) using Generative AI. With a PhD in Deep Learning and collaboration with industry experts, Alessandro uses his experience to drive innovation and business growth.

AI, ML & LLM

Machine Learning Generative AI Artificial Neural Networks (ANN) Deep Learning

Backend

DevOps

Amazon Web Services (AWS) Terraform CI/CD Pipelines Jenkins

Other

Artificial Intelligence Natural Language Processing (NLP) Statistical Modeling Amazon SageMaker Fraud Prevention Grafana Advertising Technology (Adtech)

Work history

TeleSign
TeleSign
Machine Learning Engineer
2021 - Present (4 years)
Remote
  • Scaled real-time and batch ML systems for fraud detection — led the development of multi-region risk scoring pipelines, enabling detection at scale with <40ms latency and 500 TPS, reducing delivery time by 70%.

  • Improved SMS OTP classification using LLMs — fine-tuned transformer models to enhance classification accuracy, reducing false positives by 2% and improving trust in telecom authentication.

  • Pioneered internal AI tools with RAG — built a Retrieval-Augmented Generation (RAG) system for internal documentation search, cutting information retrieval time by 20% and boosting team productivity.

Risk Modeling Fraud Prevention Generative Pre-trained Transformers (GPT) Generative AI Feature EngineeringClusteringAnomaly Detection Prompt Engineering MLOpsCI/CD Pipelines Model Development Low-latency Software Continuous Monitoring MLFlow Data ProcessingPysparkAWS GlueSQLnoSQLAmazon SageMaker AWS Lambda TerraformInfrastructure as Code (IaC) DockerKubernetesScikit LearnPytorchKerasLangChain PandasNumpyGitJenkinsLinuxAgile Leadership Architectural Design Stakeholder Engagement PythonGroovyTensorflowNatural Language Processing (NLP) Large Language Models (LLMs)
FICO
FICO
Lead Analytics Scientist
2018 - 2021 (3 years)
San Diego, United States of America
  • Scaled fraud detection infrastructure — designed and deployed high-performance pipelines capable of 2,000 transactions per second with ~100ms latency, supporting real-time fraud detection at scale.

  • Improved model accuracy using Generative AI — optimized FICO’s fraud detection algorithms with Generative AI modeling techniques, leading to a 5% boost in detection accuracy across key products.

  • Streamlined Data Science workflows — built proprietary tools to automate data analysis, increasing team efficiency by 10% and supporting ML model deployment in a regulated environment.

Fraud Prevention Credit Risk Supervised Learning Unsupervised Learning Generative Adversarial Networks (GANs) Anomaly Detection Low LatencyData AnalysisStatistical Modeling Real-time Computing Model Validation PythonScikit LearnJavaBash ScriptingData pipelinesSQLnoSQLApache Ignite TensorflowPytorchBanking & Finance Regulatory Compliance Agile WorkflowStakeholder Engagement Natural Language Processing (NLP) Generative AI Data Science
Viant Technology
Viant Technology
Data Scientist
2015 - 2018 (3 years)
Irvine, United States of America
  • Optimized digital advertising with AI — built ML solutions to improve campaign targeting and bidding strategies, increasing CTR and accuracy by 2% across multiple ad platforms.

  • Enhanced RTB inventory through ML expansion — modeled real-time bidding (RTB) supply and introduced predictive expansion strategies that boosted inventory availability by 3%.

  • Boosted engagement with cloud-based personalization — deployed scalable ML pipelines in the cloud to enhance customer engagement and retention by 15%, driving measurable business outcomes in programmatic advertising.

Advertising Technology (Adtech) Customer Segmentation User Engagement Ad Campaigns Google BigQuery Google Cloud Platform (GCP) PythonSQLPysparkAmazon Web Services (AWS) Large-Scale Computing TensorflowKerasNatural Language Processing (NLP) Supervised Learning Unsupervised Learning Deep Neural Networks Machine LearningDigital Advertising

Showcase

Real-time & Batch Risk Scoring System
Real-time & Batch Risk Scoring System

Company: TeleSign Role: Machine Learning Engineer (2021-present) TeleSign needed a scalable, multi-region Machine Learning solution for real-time fraud detection. The system had to process high-throughput user signals and deliver accurate risk scores with low latency, supporting telecom and identity verification use cases. Additionally, the team required a batch scoring capability for retrospective analysis and customer-wide risk evaluation. Led the design and implementation of a dual-mode ML risk scoring system that supports both real-time inference and scheduled batch scoring. Developed end-to-end ML pipelines using AWS SageMaker for model training, evaluation, and registry integration. Deployed scalable inference endpoints with SageMaker capable of returning predictions in under 40ms. Built batch scoring workflows using AWS Glue and PySpark to support high-volume scoring on historical data. Designed feature engineering workflows that combine real-time streaming (Kinesis) and aggregated features from transactional databases. Automated multi-region deployment using Terraform and CI/CD pipelines (Jenkins) and integrated monitoring and alerting using CloudWatch to ensure system performance and reliability. The overall end-to-end latency for real-time scoring, including feature enrichment and orchestration, is approximately 300 milliseconds. Tech stack: ML/AI: scikit-learn, XGBoost. Infra/MLOps: AWS SageMaker, Lambda, Glue, CloudWatch, Terraform, Jenkins. Data Engineering: PySpark, AWS Kinesis, DynamoDB, Athena. Languages: Python, SQL. Deployment: Multi-region CI/CD, Docker. Impact: Reduced customer model delivery time by 70% through full pipeline automation. Achieved low-latency fraud detection with SageMaker inference under 40ms and overall end-to-end response time around 300ms. Enabled scalable batch scoring for large datasets across clients and geographies. Strengthened the security and reliability of telecom identity verification products.

RAG System for Code Documentation Retrieval
RAG System for Code Documentation Retrieval

RAG System for Code Documentation Retrieval Company: TeleSign Role: Machine Learning Engineer (2021-present) TeleSign’s engineering team needed a faster and more intuitive way to navigate internal code documentation. Traditional search tools were inefficient for large and evolving codebases, leading to lost time during onboarding, debugging, and implementation. Developed and deployed a Retrieval-Augmented Generation (RAG) system tailored to internal codebases and documentation. The system indexes proprietary code, docstrings, and architectural notes by chunking and embedding them using Titan Embeddings. These embeddings are stored in OpenSearch, enabling fast semantic search. At query time, the top-k relevant chunks are retrieved and passed to Claude Sonnet via AWS Bedrock, which generates context-aware, natural-language answers. The solution is fully serverless, with back-end logic implemented using AWS Lambda, ensuring scalability, cost-efficiency, and ease of deployment. Tech stack: AWS Bedrock (Claude Sonnet), Titan Embeddings, OpenSearch, AWS Lambda, Python. Impact: Reduced average documentation retrieval time by 20%, significantly boosting developer productivity and making technical references more accessible across the engineering team.

Smart Email Encoding for Loan Fraud Detection
Smart Email Encoding for Loan Fraud Detection

Company: FICO Role: Lead Analytic Scientist (2018-2021) In application loan fraud detection, email addresses often contain subtle patterns that distinguish legitimate applicants from fraudsters. Traditional feature extraction methods failed to capture these sequential signals, limiting model accuracy and detection capability. Developed a 1D Convolutional Neural Network (ConvNet) to process email addresses as sequences of characters, allowing the model to learn informative substring patterns automatically. The model encoded emails into meaningful embeddings that were then incorporated into the overall fraud detection pipeline. After training, the TensorFlow model was serialized using Protocol Buffers (protobuf) and integrated into FICO’s proprietary Java-based inference pipeline, enabling production-grade real-time scoring. Tech stack: Python, TensorFlow/Keras, Scikit-learn, Java, Protocol Buffers, NumPy, Pandas. Impact: Achieved a 3% improvement in fraud detection accuracy for application loan risk scoring. The Deep Learning approach provided enhanced generalization for edge cases and helped reduce false negatives with minimal latency overhead in production.

Education

PhD Computer Science
PhD Computer Science
University College Dublin
2009 - 2013 (4 years)
Master's Degree, Electrical and Electronics Engineering
Master's Degree, Electrical and Electronics Engineering
Università degli Studi di Cagliari - Italy
2006 - 2009 (3 years)
Bachelor's Degree, Electrical and Electronics Engineering
Bachelor's Degree, Electrical and Electronics Engineering
Università degli Studi di Cagliari - Italy
2002 - 2005 (3 years)