1"use strict";(self.webpackChunkasifrehan_com=self.webpackChunkasifrehan_com||[]).push([[9607],{9844:(e,i,a)=>{a.r(i),a.d(i,{default:()=>s});a(6540);var n=a(781),r=a(6896),t=a(4848);function s(){return(0,t.jsx)(n.A,{title:"Experience",children:(0,t.jsxs)("main",{className:"container margin-vert--lg",children:[(0,t.jsx)("h1",{children:"Professional Experience"}),(0,t.jsxs)("div",{className:r.A.experienceItem,children:[(0,t.jsx)("h3",{children:"Senior Software Engineer (ML Infra)"}),(0,t.jsx)("p",{className:r.A.subtitle,children:"Lyra Health Inc. (Apr 2026 \u2013 Present)"}),(0,t.jsxs)("ul",{children:[(0,t.jsx)("li",{children:"Started a ML Platform Cohort to collaboratively design a ML platform for automatic model retraining for traditional and GenerativeAI models and serve"}),(0,t.jsx)("li",{children:"Architected transformative ML Platform, deployed MLFlow and Dagster services on Kubernetes on AWS with complete SSO and IAM integration, built CI/CD, Continuous Training (CT) pipelines, "}),(0,t.jsx)("li",{children:"Enabled ML Engineers and Data Scientists run ML experiments in automated manner, helped Lyra's critical ML Services responsive to supply-demand dynamics for the care providers and patients"})]})]}),(0,t.jsxs)("div",{className:r.A.experienceItem,children:[(0,t.jsx)("h3",{children:"Senior Software Engineer (MLOps + Backend)"}),(0,t.jsx)("p",{className:r.A.subtitle,children:"Ford Pro, Ford Motor Company (Jun 2021 \u2013 Apr 2026)"}),(0,t.jsxs)("ul",{children:[(0,t.jsx)("li",{children:"Evangelized containerization; built MLOps team from scratch; influenced talent mobility, architecture, data policy"}),(0,t.jsx)("li",{children:"Architected and deployed microservices on cloud platforms (GCP), built CI/CD pipelines and Infrastructure as Code (Terraform, Tekton, Helm) using VertexAI, PubSub, Cloud Run, Cloud Functions saving $200k/year"}),(0,t.jsx)("li",{children:"Built fullstack web applications (Spring Boot, FastAPI, NextJS, React) in production using TDD"}),(0,t.jsx)("li",{children:"Proactively broke down business-critical legacy monolith services worth over $100M into microservices handling over 3-5M req/month using GraphQL and ElasticSearch"}),(0,t.jsx)("li",{children:"Developed Machine Learning systems using Vertex AI, Kubeflow, and Airflow, saving over $27Million/year"}),(0,t.jsx)("li",{children:"Built & piloted fullstack Retrieval Augmented Generation (RAG) application using Large Language Model (LLM)"}),(0,t.jsx)("li",{children:"Identified and mitigated security vulnerabilities in cloud-native applications using SonarQube, 42Crunch"}),(0,t.jsx)("li",{children:"Wrote FastAPI auth middleware library using OAuth2, JWT, and integrated with enterprise IAM systems"})]})]}),(0,t.jsxs)("div",{className:r.A.experienceItem,children:[(0,t.jsx)("h3",{children:"Software Engineer / Data Scientist (Data + Algorithms)"}),(0,t.jsx)("p",{className:r.A.subtitle,children:"Ford Motor Company (May 2021 \u2013 Jun 2021)"}),(0,t.jsxs)("ul",{children:[(0,t.jsx)("li",{children:"Designed and implemented data pipelines for real-time data processing using Apache Kafka, Spark, and Hadoop"}),(0,t.jsx)("li",{children:"Developed algorithms for data analysis and machine learning model training"}),(0,t.jsx)("li",{children:"Collaborated with cross-functional teams to integrate data solutions into existing systems"})]})]}),(0,t.jsxs)("div",{className:r.A.experienceItem,children:[(0,t.jsx)("h3",{children:"Software Engineer (Mobility Research + ML Systems)"}),(0,t.jsx)("p",{className:r.A.subtitle,children:"Metropia Inc. (Sep 2015 \u2013 Mar 2018)"}),(0,t.jsxs)("ul",{children:[(0,t.jsx)("li",{children:"Helped get Google and Apple app store rating over 4-stars by finding and fixing backend and smartphone app UI"}),(0,t.jsx)("li",{children:"Built and tested SOTA Texas border crossing time prediction ML feature for smartphone app for a $408k project"}),(0,t.jsx)("li",{children:"R&D\u2019d advanced routing and navigation algorithms using Python+Java, created services using Neo4J, Kafka"})]})]}),(0,t.jsxs)("div",{className:r.A.experienceItem,children:[(0,t.jsx)("h3",{children:"Graduate Researcher (ML Research + Algorithms)"}),(0,t.jsx)("p",{className:r.A.subtitle,children:"University of Connecticut (Aug 2013 \u2013 Aug 2015)"}),(0,t.jsxs)("ul",{children:[(0,t.jsx)("li",{children:"Developed a software prototype similar to Google Maps' routing engine using crowdsourced GPS data"}),(0,t.jsx)("li",{children:"Created a prototype algorithmic framework for estimating route travel time"}),(0,t.jsx)("li",{children:"Simulated hypothetical crowdsourcing scenarios in Python to evaluate model efficacy"}),(0,t.jsx)("li",{children:"Implemented Hidden Markov Model-based GPS map-matching algorithm with 95% accuracy using a novel Confusion Matrix approach"}),(0,t.jsx)("li",{children:"Achieved over 90% accuracy in route travel time estimation using Regularized Least Squares Regression"})]}),(0,t.jsxs)("details",{children:[(0,t.jsx)("summary",{children:"Details"}),(0,t.jsxs)("p",{children:["Implemented algorithms to infer transit vehicle routes from GPS readings and detect deviations from predefined routes, providing accurate route detection every minute. Developed a Hidden Markov Model (HMM) based map-matching algorithm using the Viterbi algorithm for filtering noisy, low-frequency GPS data. All code was implemented in Python using ArcPy, open-source GIS libraries, NumPy, SciPy, and Pandas. The main objective was to predict Estimated Time of Arrival (ETA) and analyze crowd motivation.",(0,t.jsx)("br",{}),(0,t.jsx)("br",{}),"Simulated a crowdsourcing environment to predict ETA as a Trajectory Regression problem, solved with Kernel Ridge Regression. Utilized open-source GIS libraries such as GDAL/OGR, Shapely, Fiona, Pyproj, NetworkX, PyKML, ArcMap, Network Analyst, and Matplotlib for data processing and visualization. The project is hosted on GitHub."]})]})]})]})})}},6896:(e,i,a)=>{a.d(i,{A:()=>n});const n={skillsGrid:"skillsGrid_e8Tw",skillCategory:"skillCategory_BWG_",skillList:"skillList_DDum",skillTag:"skillTag_izbM",educationContainer:"educationContainer_MXe6",educationCard:"educationCard_C0Sq",schoolName:"schoolName_KYex",educationDetail
1s:"educationDetails_N6RF",certificationTitle:"certificationTitle_ZxBU",certificationsContainer:"certificationsContainer_Va7M",certificationCard:"certificationCard_u40l",certLink:"certLink_YPFt"}}}]);
Line numbers count LF bytes from the start of the resource, as the search results do. Vendor segments are library code the classifier recognised; they are stored but not indexed. Bytes are shown as Latin1 characters, one per byte.