Anirudh Vemuri

Computer Science Student & Software Engineer

I'm a Computer Science student at the University of Michigan with a passion for building high-performance systems and intelligent applications. My work spans from low-level systems programming to machine learning and full-stack development.

Currently exploring the intersection of AI and systems engineering, with experience in microservices architecture, real-time data processing, and end-to-end encryption.

Education

University of Michigan
University of Michigan
B.S.E. in Computer Science, Minor in Mathematics

GPA: 3.87

Expected May 2027Ann Arbor, MI

Relevant Coursework

Data Structures and Algorithms, Computer Organization, Object Oriented Programming, Discrete Math, Linear Algebra, Introduction to Probability Theory, Multivariable and Vector Calculus

Activities

Honors Program, Michigan Hackers Advanced ML Team, Michigan Data Science Team

Experience

Strata AI logo
Strata AI
May 2025 - Aug 2025
Software Development Intern · Ann Arbor, MI
  • Implemented 5+ microservices for an Electron-based CRM analytics platform to increase small business customer retention; attained <50 ms API latency with 99.99% uptime by leveraging Apache Kafka and Amazon EventBridge
  • Accomplished real-time customer segmentation and churn prediction with up to a 20% increase in retention, utilizing ONNX Runtime in Python for mixed-precision inference and containerized auto scaling with AWS Fargate
  • Ensured user privacy with 100% end-to-end encryption by implementing TLS 1.3 and server-side AES-256
SLV Realty logo
SLV Realty
May 2024 - Aug 2024
Software Engineering Intern · Greenville, SC
  • Developed a personalized home-listing notification pipeline used by 200+ buyers with over 50% 2-week retention, implementing custom filters including price, location, and school-zone, utilizing Flask and AWS Lambda
  • Built a buyer-agent matching system, identifying the optimal agent for each listing by scoring agents on listing alignment and buyer preference with a LambdaMART model, and automatically connecting parties after a match
  • Automated the import of 1,200+ listings into an internal dashboard by deploying a Python ETL tool
Clemson University logo
Clemson University
Jun 2023 – Aug 2023
Research Assistant · Clemson, SC
  • Increased the relevant response rate of Parkinson's disease caregiver questions by 17% through developing a SVM-based query classification and contextualization pipeline based on 2000+ samples
  • Achieved a 0.83 macro-F1 score by implementing a Bayesian hyperparameter search with Optuna TPESampler

Projects

QuickDrop
Mar 2025 – Jul 2025
C/C++, Crow, libsodium, ZSTD, TCP/UDP
  • Developed a cross-platform peer-to-peer file transfer system supporting 100+ concurrent peers with <5 ms latency through UDP-broadcast discovery, TCP handshake optimizations, and multi-threaded accept loops
  • Optimized data transfer, achieving 150 MB/s throughput with 60% average ZSTD compression per I/O chunk
  • Validated end-to-end encryption and authentication for 500k+ file chunks, maintaining <0.5 ms decryption latency with concurrent integrity checks, using Diffie-Hellman key exchange and ChaCha20-Poly encryption
  • Enabled transfers to resume <100 ms after network interruptions by implementing per-chunk state persistence
Optimize AI
Feb 2025 – Mar 2025
Python, Flask, Next.js
  • Reduced the compute cost of LLM calls by up to 30% through developing an algorithm to simplify complex queries with a multi-stage NLP-based query parser leveraging spaCy dependent parses and semantic role labeling
  • Developed an energy-benchmarking dashboard to visualize lifetime and session-level savings in various units
  • Implemented a token-based game module to reward calculated energy savings and incentivize user retention
GestureMap
Sep 2024 – Dec 2024
Python, MediaPipe, OpenCV, Tkinter
  • Enabled control of 20+ desktop actions with hand gestures with 95% accuracy through CV gesture classification
  • Integrated ASL-based text input through utilizing MediaPipe Hands tracking for <50 ms frame translation latency
  • Improved text input speed by 35% on average by integrating a seq2seq LSTM autocomplete module
  • Minimized unknown sign errors for non-standard ASL words by implementing a k-NN–based semantic map

Technical Skills

Languages

PythonC++JavaC#SwiftHTML/CSSJavaScriptTypeScriptFlutterDartSQLMatlab

Frameworks

FlaskDjangoReact (native)ElectronNode.jsSwiftUICoreMLARKitSpringSvelteQtCrow

Developer Tools

GitDockerVS CodeXcodeHerokuJenkinsKubernetesAWSJupyter NotebookEclipse

Libraries

TensorFlowPandasTkinterScikitNumPyMatplotlibBeautiful SoupPygamePyTestJinja2