Senior Data & AI Platform Engineer

Antoine Cincinnati, OH (***) Powell ***-**** ***.********@*******.*** Linkdin

Profile

· Senior Data Engineer / AI Data Platform Engineer with 10+ years of experience building production- grade data platforms, AI-powered systems, and cloud-native applications across healthcare, retail, and enterprise environments.

· Strong hands-on experience designing scalable data pipelines, ETL/ELT workflows, ingestion frameworks, validation layers, and analytics-ready data models using Python, SQL, Airflow, Spark, Kafka, dbt, Snowflake, PostgreSQL, and AWS.

· Experienced in building secure and reliable healthcare data workflows, including API-based ingestion, structured partner files, HL7/X12-style data exchange patterns, data quality automation, schema validation, and downstream reporting support.

· Skilled in deploying LLM-powered applications and RAG workflows using GPT-4, GPT-3.5, Claude, LLaMA, LangChain, LangGraph, Pinecone, FAISS, semantic search, vector embeddings, and MCP-style data access patterns.

· Strong background in cloud-native engineering with AWS, SageMaker, S3, Lambda, EKS, Docker, Kubernetes, Terraform, GitHub Actions, CI/CD, monitoring, observability, and production incident investigation.

· Product-oriented engineer who connects data engineering, AI infrastructure, backend services, and business needs to deliver practical, scalable, and trustworthy systems that support reporting, automation, analytics, and decision-making.

Experience

Senior Software Engineer / Senior Data & AI Engineer @ Spring Health Oct 2022 – Oct 2025 Remote

· Owned the design, development, deployment, and operational support of Python-based data services, backend workflows, and AI-powered systems supporting patient navigation, analytics, support automation, and internal decision-making.

· Built scalable healthcare data workflows to ingest, transform, validate, and serve structured and unstructured data across product, analytics, clinical operations, and AI use cases.

· Supported healthcare data exchange patterns involving structured partner files, API payloads, and HL7/X12-style clinical and administrative data formats used in downstream reporting and operational workflows.

· Designed production-ready backend data services using Python, FastAPI, Flask, Django, PostgreSQL, Redis, AWS, REST APIs, and GraphQL to provide reliable access to clean and reusable data.

· Implemented data quality checks and validation logic for completeness, consistency, accuracy, freshness, and schema integrity before data was used by downstream applications and AI workflows.

· Developed reusable Python components for data transformation, workflow automation, API integration, validation, error handling, and service reliability.

· Built and deployed RAG-based AI workflows using GPT-4, GPT-3.5, Claude, LLaMA, LangChain, LangGraph, Pinecone, FAISS, semantic search, and vector embeddings to improve knowledge retrieval, response grounding, and user support automation.

· Designed conversational AI workflows with memory management, prompt chaining, retrieval orchestration, and structured response handling to support reliable multi-turn user interactions.

· Contributed to MCP-style data access patterns that allowed LLM-powered workflows and internal AI agents to retrieve governed application context, structured healthcare data, and knowledge-base content through controlled service interfaces.

· Integrated LLM-powered services into production workflows with attention to response accuracy, latency, monitoring, prompt behavior, and reliability under real user traffic.

· Built user-facing and internal workflow features across React, Next.js, Redux, Tailwind CSS, WebSockets, and backend API services to connect AI/data workflows with practical product experiences.

· Implemented authentication and API security patterns using JWT Auth, OAuth2, and API rate limiting to protect backend services and support secure application access.

· Built and maintained GitHub Actions CI/CD pipelines to automate code validation, unit testing, integration testing, build checks, and deployment of Python services and data workflows.

· Used Pytest, Jest, and automated validation workflows to improve release confidence, reduce regression risk, and support repeatable production deployments.

· Deployed and operated cloud-native services on AWS using SageMaker, Docker, Kubernetes, EKS, EC2, S3, Lambda, CloudFront, and Terraform, supporting scalable environments and high service availability.

· Designed monitoring and observability practices using CloudWatch, Sentry, application logs, metrics, and alerts to detect workflow failures, latency issues, service degradation, and production anomalies.

· Investigated production issues by tracing records, API behavior, logs, metrics, and downstream impact across distributed services, then implemented durable fixes to prevent recurring failures.

· Improved performance and cost efficiency through caching, workload distribution, query optimization, API tuning, and cleaner service boundaries.

· Partnered with product managers, data teams, clinical stakeholders, and engineering leaders to translate ambiguous requirements into reliable data workflows, service designs, success metrics, and delivery plans.

· Documented data workflows, API behavior, validation rules, deployment steps, monitoring expectations, and troubleshooting procedures to improve transparency and supportability.

· Mentored engineers through code reviews, debugging support, design feedback, and guidance on Python development, testing practices, data workflows, AI service design, and production reliability.

· Contributed to a remote-first engineering culture through clear async communication, thoughtful documentation, and strong ownership of production systems. Computer Vision Engineer / Python Data Engineer @ TekValue IT Solutions Dec 2018 – Aug 2022 Remote

· Designed and implemented Python-based data and AI pipelines for a face recognition employee access system used to support secure authentication across enterprise environments.

· Built end-to-end workflows for unstructured image data, including data ingestion, preprocessing, detection, alignment, embedding extraction, validation, similarity matching, and audit logging.

· Developed backend services using Python, Flask, FastAPI, and API integrations for employee enrollment, identity verification, access decisions, and operational reporting.

· Created reusable Python processing components to standardize image preparation, feature extraction, data validation, and model feedback loops.

· Fine-tuned and adapted pre-trained computer vision models including RetinaFace and ArcFace using domain-specific datasets to improve accuracy under real-world lighting, pose, and occlusion conditions.

· Built model workflows using OpenCV, PyTorch, TensorFlow, Scikit-learn, Hugging Face, ONNX Runtime, and CoreML to support computer vision inference, model optimization, and deployment readiness.

· Designed embedding-based authentication logic using cosine similarity and calibrated thresholds to balance security requirements with user experience.

· Improved inference latency by approximately 25% through preprocessing optimization, model compression, pipeline tuning, and more efficient data handling.

· Built monitoring and continuous improvement workflows to review production feedback, detect edge cases, and refine model performance over time.

· Implemented privacy-conscious data handling by storing encrypted embeddings instead of raw images where possible, supporting secure handling of sensitive identity data.

· Collaborated with backend, mobile, infrastructure, and security-focused teams to deliver a scalable, high-availability system for real-time authentication.

· Supported production troubleshooting by analyzing logs, model outputs, matching behavior, and system performance to identify root causes and recommend long-term fixes.

· Participated in code reviews, technical discussions, documentation, and deployment planning to improve maintainability and production readiness.

Data Scientist / Data Engineer @ Walmart

Dec 2016 – Nov 2018 Toledo, OH

· Built and maintained production ETL pipelines using Python, SQL, Apache Airflow, Kafka, and Spark to process large-scale retail data for analytics, reporting, and business decision-making.

· Developed batch and near real-time data workflows to ingest and transform clickstream, transaction, customer behavior, search, cart, sales, and inventory datasets.

· Built scalable data transformation logic using Python, SQL, Spark, Pandas, NumPy, and reusable pipeline components to convert raw operational data into analytics-ready datasets.

· Developed dbt-style modular transformation models and SQL-based reporting layers to standardize business metrics across sales, inventory, marketing, and customer behavior analytics.

· Created curated data models and analytics-ready tables that improved consistency across Tableau, Power BI, Streamlit, D3.js, and internal reporting workflows.

· Optimized Snowflake and PostgreSQL schemas, queries, indexes, and reporting tables to improve dashboard performance, reduce latency, and support reliable daily reporting.

· Implemented data validation checks to identify missing records, duplicate values, inconsistent metrics, schema issues, freshness delays, and quality problems before they impacted downstream dashboards.

· Developed reconciliation logic across raw source data, transformed datasets, reporting tables, Tableau dashboards, and Power BI reports to improve trust in business outputs.

· Monitored pipeline execution, investigated workflow failures, and resolved data freshness, data integrity, and performance issues during high-priority reporting periods.

· Built Python-based Flask and FastAPI data services to expose cleaned and structured datasets to dashboards, reporting applications, and internal analytics tools.

· Delivered Tableau and Power BI dashboards used by business teams to monitor sales performance, conversion rates, inventory movement, customer behavior, and operational trends.

· Partnered with analysts, product stakeholders, and business teams to define data requirements, reporting logic, validation rules, and delivery timelines.

· Supported business analysis by identifying trends, anomalies, and correlations across customer behavior, product performance, inventory movement, and conversion data.

· Prepared reliable datasets for experimentation, product analysis, marketing insights, and operational decision-making.

· Improved documentation around pipeline logic, data definitions, schemas, reporting dependencies, validation checks, and troubleshooting procedures. Education

University of Toledo 2012-2016 Toledo, OH

Bachelor's degree in Computer Science

Skills & Abilities

· Programming & Querying: Python, SQL, PySpark, Pandas, NumPy, TypeScript, JavaScript, Bash, Complex SQL Queries, Query Optimization, Automation Scripts

· Data Engineering: ETL, ELT, Data Pipelines, Data Ingestion, File Ingestion, API-Based Ingestion, Batch Processing, Near Real-Time Processing, Data Transformation, Data Integration, Data Modeling, Schema Design, Data Warehousing, Data Marts, Data Lake Concepts, Data Lineage, Metadata Documentation

· Transformation & Orchestration: dbt, Apache Airflow, Kafka, Apache Spark, PySpark, Workflow Automation, Stream Processing Concepts, Event-Driven Data Workflows, Pipeline Scheduling

· Cloud & Data Platforms: AWS, SageMaker, S3, EC2, EKS, Lambda, CloudFront, CloudWatch, Snowflake, Databricks, PostgreSQL, MySQL, MongoDB, Redis, Firebase, RDBMS, NoSQL

· Data Quality & Governance: Data Validation, Data Quality Checks, Completeness, Accuracy, Consistency, Freshness, Schema Integrity, Data Reconciliation, Data Profiling, Data Integrity Troubleshooting, Data Contracts, Data Governance, Secure Data Handling

· CI/CD & DevOps: GitHub Actions, Git, CI/CD, Automated Testing, Pytest, Jest, Unit Testing, Integration Testing, Code Reviews, Branching Strategies, Release Management, Docker, Kubernetes, Terraform, Vercel, Nginx

· Monitoring & Reliability: Observability, Logs, Metrics, Alerts, CloudWatch, Sentry, Grafana, Pipeline Monitoring, Incident Investigation, Root-Cause Analysis, Performance Optimization, Cost Optimization, Production Support

· AI / ML / GenAI Data Systems: LLMs, GPT-4, GPT-3.5, Claude, LLaMA, LangChain, LangGraph, RAG, MCP, FAISS, Pinecone, Semantic Search, Vector Embeddings, Memory Management, Chaining, Prompt Engineering, LLMOps, MLOps, Hugging Face, PyTorch, TensorFlow, Scikit-learn, OpenCV, CoreML, ONNX Runtime

· BI, Frontend & Analytics: Power BI, Tableau, Streamlit, D3.js, React, Next.js, Redux, Tailwind CSS, Dashboard Development, Reporting Layers, Business Intelligence, KPI Reporting, Customer Behavior Analytics, Operational Analytics

· Backend & APIs: FastAPI, Flask, Django, Express.js, REST APIs, GraphQL, Microservices, WebSockets, RabbitMQ, Celery, JWT Auth, OAuth2, API Rate Limiting

Contact this candidate