8000 Dinesh7K · GitHub
[go: up one dir, main page]

Skip to content
View Dinesh7K's full-sized avatar

Block or report Dinesh7K

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
7499
Dinesh7K/README.md

Welcome to My GitHub Profile!

  • 👋 Hi, I’m @Dinesh7K
  • 👀 I’m interested in distributed systems, AI inference infrastructure, scalable backend engineering, and applied AI.
  • 🌱 Currently building TinyServe, an LLM inference profiler measuring prefill-decode disaggregation under simulated WAN latency — and preparing to start an MSc in Computer Science (Future Networked Systems) at Trinity College Dublin (Sept 2026).
  • 💞️ I’m looking to collaborate on AI inference systems, distributed computing research, and automation frameworks.
  • 📫 How to reach me:

About Me

I'm a Software Development Engineer with 3 years of production experience at Samsung Electronics, where I was sole architect of a real-time AI chat engine (Kafka, Redis Streams, SSE) serving e-commerce platforms across two regional markets. My background spans distributed backend systems, event-driven architecture, and quality-automation frameworks. I'm now shifting focus toward AI inference infrastructure — both through independent research (TinyServe) and an incoming MSc at Trinity College Dublin.


Currently Building

TinyServe — LLM Inference Profiler Profiling prefill-decode disaggregation for LLM serving under simulated WAN latency (tc netem), measuring the RTT crossover point at which disaggregated inference stops being worth it. Benchmark pipeline live: prefill 262.3ms, decode 28.7ms/token, throughput 23.9 tok/s, KV-cache scaling 44MB → 704MB (128 → 2048 tokens).


Skills & Technologies

  • Languages: TypeScript, JavaScript (Node.js), Python, Java, SQL, Dart
  • Backend & Distributed Systems: NestJS, Fastify, Kafka, Redis (Cluster + Streams), RabbitMQ, REST APIs, GraphQL, Express.js, Django, Flask, Spring Boot, Hibernate
  • Databases: PostgreSQL, MongoDB, MySQL, CockroachDB, Redis
  • Streaming & Real-Time: Server-Sent Events (SSE), event-driven architecture, cursor-based pagination
  • AI / ML: LangChain, LangGraph, RAG, MCP, prompt orchestration
  • Test Automation: Playwright, Selenium, Appium, WebDriverIO, TestNG, Rest Assured
  • CI/CD & Cloud: Jenkins, GitHub Actions, Docker, AWS (EC2, S3, Lambda), Git
  • Observability: Grafana, Kibana, OpenSearch
  • Tools: Postman, Android Studio, VS Code, IntelliJ

Feel free to explore my repositories and reach out for collaborations or discussions!

Popular repositories Loading

  1. Dinesh7K Dinesh7K Public

    Config files for my GitHub profile.

  2. Python-function-ex_1 Python-function-ex_1 Public

    Python

  3. AWS-website-hosting AWS-website-hosting Public

    Hosting a Employee database using EC2,RDS,S3

    Python

  4. MuleSoft-Internship MuleSoft-Internship Public

    Connect to the SQLite database (or any Database you know): Learn how to download SQLiteJDBC driver and connect to an existing SQLite database using JDBC. Creating a new SQLite database – Learn how …

    Python

  5. AWS-web-hosting AWS-web-hosting Public

  6. AI_chatbot AI_chatbot Public

    HTML

0