Walgreens: Data Engineer

LOCATION

TX

SALARY

$100000 - $150000 (Yearly)

COMPANY

Walgreens

DEPARTMENT

Data

EMPLOYMENT TYPE

Other

MINIMUM LEVEL OF EXPERIENCE

Senior Leadership (overseeing multiple Department Directors. Ex: Campaign Manager, Coordinated Manager)

APPLICATION INSTRUCTIONS

Dear Hiring Manager, I am excited to apply for the AI Engineer/Machine Learning Engineer position at your company. With experience building production-grade AI systems, Retrieval-Augmented Generation (RAG) pipelines, LLM agents, and scalable cloud applications, I enjoy transforming cutting-edge AI capabilities into reliable products that solve real business problems. Most recently, as a Machine Learning Engineer at Drexel Dornsife School of Public Health, I designed and deployed a production-grade RAG platform that improved retrieval quality, reduced off-topic responses, and enabled researchers to efficiently query healthcare documents using natural language. I also built LangGraph-based AI agents, developed FastAPI services on Google Cloud Platform, implemented automated LLM evaluation pipelines, and integrated secure deployment workflows using Docker, GitHub Actions, and MLflow. These projects strengthened my expertise in production AI, model evaluation, retrieval optimization, and secure AI delivery. Previously, as an AI Engineer at Grayson Sky, I developed a Vertex AI-powered research agent that combined RAG, function calling, and external APIs to automate competitive intelligence workflows. By optimizing retrieval strategies and intelligent model routing, I significantly improved response times while reducing inference costs. Earlier in my career, I worked as a Full-Stack Software Engineer, building scalable web applications and secure backend APIs with React, TypeScript, Node.js, Python, and PostgreSQL, giving me a strong software engineering foundation that complements my AI expertise. What excites me most about your team is the opportunity to work on ambitious AI products that have meaningful real-world impact. I enjoy collaborating across engineering and product teams, rapidly iterating on user feedback, and building systems that are scalable, reliable, and trustworthy. I am eager to contribute my experience with LLMs, RAG architectures, cloud infrastructure, and modern software engineering practices while continuing to learn and grow alongside a world-class team. Thank you for your time and consideration. I would welcome the opportunity to discuss how my background and passion for AI engineering can contribute to your organization. I look forward to hearing from you.

APPLY BY

October 1, 2026

APPLICATION LINK

MAAZ AHMED BINTHURI Philadelphia, PA | (445) 272-8515 | maazbinthuri9@gmail.com | linkedin.com/in/maazbinthuri | github.com/maazbinthuri SUMMARY AI Engineer and Machine Learning Engineer with experience building production-grade RAG systems, LLM agents, healthcare research tools, and full-stack cloud applications. Skilled in LangGraph, Vertex AI, FastAPI, GCP, Azure, PostgreSQL, pgvector, Docker, GitHub Actions, MLflow, React, TypeScript, Node.js, and Python. Strong background in secure AI delivery, retrieval optimization, model evaluation, API development, and stakeholder-focused product execution. TECHNICAL SKILLS Languages: Python, SQL, TypeScript, JavaScript Backend & APIs: FastAPI, REST APIs, async I/O, Node.js Databases & Retrieval: PostgreSQL, pgvector, FAISS, embeddings, semantic search LLM & ML: RAG, LangGraph, function calling, prompt engineering, LLM evaluation (groundedness and relevance checks); models: Claude, Gemini Cloud & Tooling: GCP (Vertex AI), Azure (Functions, Static Web Apps), Docker, GitHub Actions, MLflow Frontend (working knowledge): React, Vite, Tailwind, React Native (Expo) AI-assisted development: Claude Code, Cursor EXPERIENCE Drexel Dornsife School of Public Health Machine Learning Engineer Philadelphia, PA Nov 2024 – Dec 2025  Engineered a production-grade RAG pipeline using pgvector, hybrid search, embeddings, chunk optimization, and reranking, reducing off-topic LLM responses by 35% for internal research queries.  Built a LangGraph-based agent workflow for retrieval, summarization, and verification across healthcare research documents, cutting manual review effort by 40%.  Deployed LLM services through FastAPI on GCP with async processing, connection pooling, and optimized API handling, maintaining p95 latency near 1 second.  Created automated evaluation checks for groundedness, relevance, and hallucination risk, integrating scores into CI/CD and tracking experiments in MLflow for reproducible model releases.  Containerized AI services with Docker and configured GitHub Actions for testing, validation, and staged deployments, using Claude Code to accelerate refactoring and test generation.  Strengthened secure AI delivery for sensitive health data by implementing RBAC, retrieval-layer redaction, access controls, and privacy-aware data handling across the research platform. Grayson Sky AI Engineer (Contract) Philadelphia, PA Apr 2025 – Jun 2025  Developed a Vertex AI-powered research agent combining RAG, function calling, internal knowledge sources, and external API connectors to generate competitive intelligence summaries, reducing sales research turnaround by 45%.  Optimized retrieval performance through embedding cache design, batched inference calls, and intelligent routing to lower-cost LLMs, improving response speed by 35% while reducing GenAI operating spend by 28%.  Automated release workflows with GitHub Actions, unit testing, integration validation, and deployment gates, eliminating manual checklist steps and cutting production rollout errors by 30%.  Partnered with go-to-market stakeholders to refine brief structure, source coverage, tone, and output quality based on user feedback, aligning agent results with sales enablement needs. Bespoke Digitals Full-Stack Software Engineer Bengaluru, India Jan 2021 – Aug 2023  Delivered full-stack applications for 6 business engagements across e-commerce, logistics, and operations platforms using React, TypeScript, Node.js, Python, PostgreSQL, and responsive UI architecture.  Architected secure REST APIs with JWT authentication, rate limiting, structured request logging, and backend validation, improving API reliability by 30% for a high-traffic deployment.  Redesigned PostgreSQL schemas, migrations, indexing strategies, and query patterns, eliminating N+1 performance issues and reducing page-load delays by 40%.  Served as the primary engineering partner for two accounts, translating business needs into technical specifications while preventing scope changes that risked breaking production workflows.  Mentored a junior developer through code reviews, debugging sessions, and feature walkthroughs, accelerating onboarding by 25% on a long-running delivery project. PROJECTS Outlier Detection for Investment Signals Drexel University · Sep 2023 – Jun 2024  Trained isolation forest and autoencoder models to flag unusual signals in a historical investment dataset, and compared them against a logistic-regression baseline.  Served the best model through a FastAPI and Docker setup and tracked model versions in MLflow.  Built a small Streamlit dashboard with SHAP attributions to show why a given example was flagged. Multi-Tenant Student Progress Platform (SaaS) 2026  Built a multi-tenant platform for private schools on Azure (Functions, Static Web Apps, PostgreSQL Flexible Server) with five role tiers and tenant-scoped data isolation enforced through JWT claims.  Wrote the serverless API in Node.js and TypeScript (Azure Functions v4) with custom JWT auth, bcrypt hashing, rate-limited login with timing-safe checks, and admin-managed account provisioning.  Built the frontend in React 18 with Vite, TypeScript, and Tailwind, using TanStack React Query for data fetching and cursor-based pagination.  Set up GitHub Actions CI/CD with type checking on every merge and automated deployment to Azure, with post-deploy health checks. EDUCATION Drexel University, M.S. in Cybersecurity Presidency University, B.S. in Computer Science

JOB DESCRIPTION

Design, develop, and maintain scalable data pipelines and data solutions using Python, SQL, Spark/PySpark, Databricks, Snowflake, Airflow, dbt, and cloud technologies. Develop batch and near-real-time data ingestion and transformation processes, implement data quality and validation checks, and optimize data processing for performance and scalability. Work with cross-functional teams to translate business requirements into reliable data solutions that support analytics, reporting, and decision-making. Troubleshoot production issues, monitor pipeline performance, document data workflows, and collaborate with other developers and platform teams to support ongoing maintenance. Contribute to modernization of legacy ETL processes and migration to cloud-based data