Skip to content
View Harsh23Kashyap's full-sized avatar
💻
Always here...
💻
Always here...

Block or report Harsh23Kashyap

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. Markdown is supported. 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
Harsh23Kashyap/README.md
Header
Software Development Engineer II @ Amazon · marketplace compliance, backend systems & LLM agents · Bengaluru, India

Portfolio LinkedIn LeetCode Topmate Email


About Me

Coding

  • SDE II at Amazon, working on large-scale compliance infrastructure
  • Previously SWE II at Apple: macOS tooling, 5G protocol testing, LLM triage automation - 80% adoption on internal tools, 40% faster incident resolution, $720K annual savings
  • Earlier: PayPal full-time; internships at Apple, Tata 1mg, Cisco, Licious, YASH Technologies
  • Open-source engineering across RAG and agent infra: retrieval correctness, agent runtime hardening, plugin triggers, sandbox safety, observability, protocol tooling - mostly in RAGFlow, Dify, Langfuse, NDN, Infinity, CustomNerd
  • Research with NYU, WSU, UCLA, UBC, Edinburgh - CustomNerd accepted at MDPI Electronics, JobMatch in preparation for JAAMAS
  • B.E. CSE, Thapar Institute - CGPA 9.71, top 0.5% merit scholarship
  • 1,723 LeetCode (568 easy / 916 medium / 239 hard, rating ~1,693) · 450+ Topmate sessions at 4.3/5

Currently

Focus Details
Building Large-scale compliance infrastructure
Open-source work Retrieval correctness · agent runtime hardening · plugin triggers · sandbox safety · observability · protocol tooling
Exploring RAGFlow · LangGraph · Dify · Infinity · pydantic-ai · OpenHands · llama_index · fastmcp · together-python · openinference · Phoenix · Ragas · Qdrant
Research CustomNerd framework (NYU, accepted at MDPI Electronics) · JobMatch (JAAMAS, in preparation) · Odyssey / DataFusion cost modelling (Edinburgh) · ScientficPerplexity (UBC)

Where I'm Heading

Open-source contributions and research directions I'm pushing into over the next 6–12 months.

Open Source Upstream Projects Repositories

Open Source

Track Direction
RAG infra infiniflow/ragflow — agent inputs, DeepDoc parsing, clustering, and retrieval-quality edge cases.
Agent frameworks langgenius/dify, dify-sandbox, and dify-official-plugins — sandboxing, plugin auth, and model-provider plumbing.
LLM observability langfuse/langfuse and the neatlogs SDKs — endpoint validation, transport replay guards, SDK init consistency, span routing, and provider isolation. Interested in OTel-native tracing, evals, and feedback loops.
Vector & AI-native DBs qdrant-client, infinity, and ragas — evaluation harnesses for CustomNerd outputs.
Protocols & mobility named-data/ndnd security/CRL work · background in 5G protocol testing.

Research

  • CustomNerd — accepted at MDPI Electronics
  • JobMatch — in preparation for JAAMAS
  • Odyssey — cost-model work with the University of Edinburgh
  • ScientficPerplexity — with UBC

Focused on RAG systems, agent frameworks, observability, protocol tooling, and practical reliability work in open-source codebases.


Experience

Full-Time

Company Role Period
Amazon Amazon Software Development Engineer II Jul 2026 – Present
Apple Apple Software Engineer II Dec 2023 – Jun 2026
PayPal PayPal Software Engineer Jul 2023 – Oct 2023
Internships
Company Role Period
Apple Apple Software Developer Engineering Intern Jan 2023 – Jun 2023
Tata 1mg Tata 1mg Engineering Intern Oct 2022 – Nov 2022
Cisco Cisco Technical Undergraduate Intern Jun 2022 – Jul 2022
Licious Licious Software Developer Intern Jan 2022 – May 2022
YASH YASH Technologies Software Engineering Intern Jul 2021 – Sep 2021
Research
Institution Focus
NYU New York University CustomNerd · DietNerd · WirelessNerd · InvestorNerd · OperationsNerd · HallucinationNerd · NewsNerd
WSU Washington State University Agentic job matching · semantic search · fairness analysis
UCLA University of California, Los Angeles NDN (Named Data Networking) · Ownly
Edinburgh University of Edinburgh Odyssey / DataFusion cost model (Prof. Boris Grot)
Thapar Thapar Institute HS Pannu — demosaicing research
UBC University of British Columbia ScientficPerplexity — scientific literature query system (Prof. L.A.K.S.)

Publications

Work Venue Status
CustomNerd: A Framework and Tool for Fast Deployment of Production-Ready Expertise-Based QA Systems MDPI Electronics, 2026 First author, accepted
JobMatch: An Agentic Multi-Role Platform for Explainable Job-Candidate Matching JAAMAS Co-first author, in preparation
InvestorNerd and NewsNerd NYU, Prof. Dennis Shasha Contributing author, in preparation

Tech Stack

Core technologies I use day-to-day — not an exhaustive list.

Languages & Backend

Swift SwiftUI Python Go C++ TypeScript SQL

Cloud, Data & AI

AWS Docker RAG FAISS

Web & UI

React FastAPI JavaScript macOS

Tools & Observability

Git OpenTelemetry Langfuse Splunk Jenkins


Projects

Built by Me

Custom-Nerd Job-Matching-Agentic Odyssey

daily-contribution-bot Mailer LLD

Open Source — RAG & Agents

RAGFlow
RAGFlow
RAG engine
Dify
Dify

sandbox · plugins
LangGraph
LangGraph
Resilient agents
Infinity
Infinity
AI-native DB
ndnd
ndnd
Named-data net
FastMCP
FastMCP
MCP server tooling
Together Python
Together Python
LLM SDK fixes

Open Source — Observability & Mobility

Langfuse
Langfuse
LLM evals & observability
Neatlogs
Neatlogs
Python · Go · TypeScript SDKs
OpenInference
OpenInference
Open LLM tracing

Activity

GitHub

GitHub Stats

LeetCode

Leetcode Stats

More stats

GitHub Streak Top Languages


Achievements

Open Source Contributions YTD IICC Innovation Deck TIET Merit

GitHub achievements

Pair Extraordinaire Quickdraw Pull Shark YOLO


Education

School Degree Period Score
Thapar Institute of Engineering and Technology B.E. Computer Science 2019 – 2023 CGPA 9.71
Mount Assisi School Class XII (ISC) 2017 – 2019 96.25%
Mount Assisi School Class X (ICSE) 2015 – 2017 94.33%

Certificates & Resume

Resume Certificates


Beyond Code

Hobbies

Cricket · F1 · Treks · Gym · Cooking · Reading

Volunteering

TICC (Vice Lead Ambassador) · DiiDi · IDIA

Pinned Loading

  1. Portfolio Portfolio Public

    HTML 4

  2. CodeClue CodeClue Public

    JavaScript 2

  3. LeetCode LeetCode Public

    Collection of LeetCode questions to ace the coding interview! Harsh Kashyap LeetCode Profile - https://leetcode.com/Harsh23Kashyap/

    C++ 2

  4. ragflow ragflow Public

    Forked from infiniflow/ragflow

    RAGFlow is a leading open-source Retrieval-Augmented Generation (RAG) engine that fuses cutting-edge RAG with Agent capabilities to create a superior context layer for LLMs

    Go 1