Fjk A.

Key Skills

Software

Other

Top Subject Matter

AI-ready data pipelines for fraud detection

network analytics

and customer analytics

Top Data Types

Text

Document

Top Task Types

Data Collection

Freelancer Overview

Lead Data Engineer — T-Mobile (Data Lake & Analytics Platform; AI-RAN; Scam Shield). Brings 13+ years of professional experience across complex professional workflows, research, and quality-focused execution. Core strengths include Other. Education includes Bachelor’s Degree, Stony Brook University (2013). AI-training focus includes data types such as Computer Code and Programming and labeling workflows including Data Collection.

Labeling Experience

Lead Data Engineer — T-Mobile (Data Lake & Analytics Platform; AI-RAN; Scam Shield)

OtherData Collection

Led enterprise-scale data and AI platform initiatives that produced labeled/curated datasets for fraud detection, customer interaction analytics, and network intelligence. Built and optimized ETL/ELT pipelines and governance controls to ensure data quality and auditability for downstream AI training and decisioning. Orchestrated secure ingestion, real-time processing, and validation workflows to support reliable model inputs and continuous improvement. • Implemented ETL/ELT ingestion and transformation using Spark and Python for structured/unstructured data. • Established automated data validation, lineage, schema tracking, and quality checks for regulatory compliance. • Built real-time streaming pipelines with Kafka/Spark for telemetry/event analytics and automated alerting. • Developed secure SFTP/batch transfer workflows with monitoring, error handling, and retries.

2020 - Present

Sr. Data Engineer — American Express (Fraud Detection; Offers Personalization)

OtherData Collection

Designed and delivered large-scale data engineering platforms that supported AI-driven fraud detection and personalization by producing ML-ready datasets. Built streaming and batch pipelines to transform raw transaction and customer data into curated features suitable for model training and integration. Implemented data validation, lineage, and governance practices to ensure consistent, high-quality inputs for AI systems. • Engineered Kafka-based streaming pipelines for real-time fraud risk scoring and decisioning. • Built Spark Streaming workflows with fault tolerance and low-latency processing for transaction traffic. • Developed feature engineering pipelines to create ML-ready datasets from raw card transaction data. • Created enterprise data lake and ETL pipelines with automated validation and reconciliation across streaming and batch jobs.

2017 - 2020

Data Engineer — DataDog (Observability/AIOps data pipelines)

OtherData Collection

Built scalable batch and streaming ETL pipelines to prepare clean, structured time-series data that enabled anomaly detection, forecasting, and AIOps model inputs. Developed ingestion and transformation layers that ensured data quality through schema enforcement and consistency checks. Supported downstream analytics and automated monitoring by maintaining reliable production data pipelines. • Ingested, processed, and enriched high-cardinality observability data (metrics, logs, traces) at scale via Python ETL. • Implemented Kafka-based distributed ingestion systems for real-time and near-real-time processing. • Created transformation and aggregation layers for time-series data to support forecasting and anomaly detection. • Added data quality validation, schema enforcement, and consistency checks for reliability across observability pipelines.

2014 - 2017

Education

Work History