Ravi Kishan/Software Engineer

ravi.ai›generating response…

I rebuild the layers most people take for granted.

Software engineer drawn to the systems others treat as magic — a UI runtime, a language interpreter, a container runtime and a distributed datastore, all built from scratch. The fastest way I understand a system is to rebuild it.

Agentic AI Engineer @ Zimyo200 stars · 58 reposPatent holder
◇hallucination check: none found · 99.2%
Ravi Kishan
Ravi Kishanopen to work
●Patent holder
●3,500+ npm downloads
●Gold Medalist
0.0×
backtest speedup — SIMD, 18s → 4.2s
0%
LLM inference cost cut at Zimyo
0+
DSA problems solved
0★
GitHub stars across 58 repos
TypeScript/Go/Rust/Python/Java/C++/LangGraph/PyTorch/RAG/FAISS/gRPC/Kafka/PostgreSQL/Redis/Kubernetes/CUDA/Next.js/SIMD/TypeScript/Go/Rust/Python/Java/C++/LangGraph/PyTorch/RAG/FAISS/gRPC/Kafka/PostgreSQL/Redis/Kubernetes/CUDA/Next.js/SIMD/

Built from first principles

Systems, not just apps.

A runtime, a search engine, a cache, a language, a distributed store and a load balancer — each rebuilt from the ground up.

All 58 repositories on GitHub
UI Runtime

Relax.js

A React alternative in TypeScript: fine-grained signals/effects, a deterministic scheduler with priority lanes + budgets, and a Babel-compiled fast path with SSR, hydration and SSG.

35% faster than React · 3,500+ npm downloads
TypeScriptBabelSSRsource
Search Engine
28

RelaxSearch

A lightweight full-text search engine in Go with an Elasticsearch-style inverted index, a web crawler and a ranking algorithm over indexed documents.

inverted index · crawler · ranking
GoElasticsearchsource
In-Memory Datastore
17

Redis-Clone

A Redis server reimplemented in Rust and Go — RESP protocol, core data structures and an event loop — because rebuilding it is the fastest way to actually understand it.

RESP protocol · single-threaded event loop
RustGosource
Interpreted Language

RelaxLang

A programming language built from scratch in Java/C — lexer, parser, AST and tree-walking interpreter — inspired by Lox, shipped in a Dockerized execution environment.

lexer → parser → AST → interpreter
JavaCDockersource
Distributed Datastore
3

Distributed KV Store

A scalable, fault-tolerant key-value store in Go with sharding, replication and multithreaded request handling across nodes for high availability under node failure.

sharding · replication · high availability
GoConcurrencysource
Traffic Router
4

Load Balancer

An NGINX/HAProxy-style load balancer in TypeScript — round-robin and weighted strategies, health checks and reverse-proxying across backend pools.

round-robin · weighted · health checks
TypeScriptNode.jssource

The track record

Where it shipped.

Education

VIT Vellore

VIT Vellore

2024 — 2026

MCA — Master of Computer Applications

GPA 9.5 / 10

PIMR, Gwalior

PIMR, Gwalior

2021 — 2024

BCA — Bachelor of Computer Applications

GPA 9.6 / 10 · Gold Medalist

R.S.B. Inter High School

R.S.B. Inter High School

2019 — 2021

Higher Secondary (12th), Science — BSEB

74%

R.S.B. Inter High School

R.S.B. Inter High School

2017 — 2019

Matriculation (10th) — BSEB

84%

Highlights

  • MCA, VIT Vellore — GPA 9.5/10
  • Graduation Gold Medalist
  • Named inventor · published Indian patent
  • Microsoft Learn Student Ambassador
Zimyo

Agentic AI Engineer

Zimyo
Apr 2026 — Present
Gurugram
  • Built an agentic AI platform for HRMS automation on LangChain + LangGraph — natural-language multi-step workflows across payroll, attendance and employee-lifecycle modules.
  • Engineered a dynamic API-ingestion engine that parses REST schemas and auto-generates executable workflow graphs, killing manual config for 5+ HR modules.
  • Cut LLM inference cost 70% by consolidating multi-turn generation into a single schema-constrained call.
Arrowhead Capital Management

Quantitative Developer Intern

Arrowhead Capital Management
Jul 2025 — Apr 2026
Mumbai
  • Designed a vectorized backtesting engine over 5M+ time-series records using SIMD intrinsics — 18s → 4.2s (4.3× speedup).
  • Built ETL pipelines with multi-layer validation + caching (+30% research throughput) and rolling-window risk analytics (Sharpe, max drawdown, VaR).
Chiti Infotech

Full-Stack Developer Intern

Chiti Infotech
Jan 2023 — Sep 2023
Gwalior
  • Migrated a legacy PHP monolith to a modular React SPA (40% faster frontend) and reworked the REST layer with caching (−25% latency).

Publications

My research and patents

Research that made it past review — a published patent application on applied AI over Indian epics.

Indian Patent ApplicationPublished

A Multilingual Chatbot for Indian Epics Using Generative AI and LLMs

App. No. 202541117128 · Filed Nov 2025 · Published 19 Dec 2025

A RAG system over the Bhagavad Gita reaching >95% retrieval accuracy across 5 languages — built with OpenAI embeddings, LangChain and FAISS/Pinecone, and evaluated with BLEU and BERTScore.

RAGLLMsNLPVector Search

On GitHub

9 things shipped in the last 12 months

September 2026

July 2026

June 2026

May 2026

March 2026

February 2026

November 2025

July 2025

June 2025

May 2025

January 2025

September 2024

August 2024

April 2024

January 2024

Open to hard problems

Got a system worth
building right?

Distributed backends, AI agents, or performance work that needs to go fast. Let's talk.

0
changedesignexperienceinteractiontomorrowultralifechanceopportunitymomentimmersivechangedesignexperienceinteractiontomorrowultralifechanceopportunitymomentimmersivechangedesignexperienceinteractiontomorrowultralifechanceopportunitymomentimmersivechangedesignexperienceinteractiontomorrowultralifechanceopportunitymomentimmersivechangedesignexperienceinteractiontomorrowultralifechanceopportunitymomentimmersive