PORTSprint 26.7Available

AI engineer & Full-stack Developer

I ship AI systems the same way a good team ships software: scoped tickets, measured outcomes, no mystery work. Retrieval, agent orchestration, evaluation, and the product surfaces around them.

View the boardActivity log
  • React
  • Typescript
  • Python
  • LangGraph
  • FastAPI
  • TypeScript
  • Next.js
  • Postgres
  • Docker

Details

Assignee
A. Bhavsar
Reporter
Open to inbound
Labels
RAG PipelinesMulti-agentGuardrails
Experience
7+ yrs
Location
Remote · UTC+0

Activity — check-ins, last 12 months

523 commits · 42 longest streak
@aniketbhavsarHover a day for its count
Aug 2025LessMoreAug 2026

Sprint stats

214

Repositories

610

Contributions

15

Repos contributed

26

Day streak

Projects — delivery board

9 issues · 57 story points
Done3

ScholarNotesPro — RAG research workspace

NotebookLM-style research app: PDF + YouTube ingestion, inline citations, and generated summaries, timelines, mind maps and study guides.

RAGMulti-userCitations
Next.jsFastAPIMongoDBPinecone
PORT-08Demo13

Daybreak — AI calendar scheduler

A terminal LangGraph scheduler rebuilt as a multi-user web app: per-user Google OAuth, SSE streaming, split-screen chat and agenda.

AgentsGoogle OAuthSSE
Next.jsLangGraphPrismaSupabase
PORT-07Demo8

Persona chat — AI tech-educator simulator

Streaming chat that simulates the teaching style of two Hindi/Hinglish tech educators, with a persona toggle and prompt storage in Postgres.

PersonasStreamingHinglish
Next.jsOpenAINeon
PORT-09Demo5
In progress1

aniketdev.blog — notebook book-blog

A book-style reading experience: markdown compiled to typed blocks, a page-flip reader, and a FastAPI + Neon backend with a markdown→blocks compiler.

Full-stackBook UICI/CD
Next.jsreact-pageflipFastAPINeon
PORT-06Demo13
Open source2

Self-Consistency Answer Engine

Fans one prompt out to OpenAI, Claude and Gemini in parallel, then synthesizes a single answer with Claude — streamed live.

Multi-LLM3 models
Next.jsLangChain JSSSE
PORT-05Demo5

AI Expense Tracker (generative-ui)

Conversational expense tracker with generative UI, JWT auth and per-user data isolation on a persistent SQLite volume.

Gen-UIPer-user
ExpressLangGraphSQLite
PORT-04Demo5
Backlog3

Live stock leaderboard (Redis)

Real-time NSE/BSE leaderboard on Redis sorted sets, with decoupled WebSocket write and button-click read layers.

Idea
RedisWebSocketNode
PORT-033

“Ask my portfolio” chatbot

A small RAG agent that answers questions about my projects from this board’s own data and my write-ups.

Idea
LangChainPinecone
PORT-023

Cost-aware model router

Routes each request to the cheapest model that clears a quality bar, with per-tenant budgets and live fallback.

Idea
LiteLLMRedis
PORT-012

System design — write-ups

7 posts · click a card to read the summary

Architecture decisions I've had to defend, written up after the fact. Each opens with the problem, the trade-off I took, and what it cost.

System DesignSD-01

Conflict-free Replicated Data Type

CRDT stands for Conflict free Replicated Data Type. It is a data structure designed for distributed systems where multiple replicas can…

4 min read · Aug 2026Open →
System DesignSD-02

Kafka

Kafka is a distributed event streaming platform that allows multiple services to communicate through a durable, partitioned, and scalable…

3 min read · Aug 2026Open →
System DesignSD-03

Event-Driven

Event driven architecture is a software architecture where services communicate by publishing and reacting to events instead of directly…

5 min read · Aug 2026Open →
System DesignSD-04

Cache Stampede Problem

A cache stampede happens when many requests simultaneously discover that the same cached data is expired or missing and all try to rebuild…

4 min read · Aug 2026Open →
System DesignSD-05

Thundering Herd

Every cache miss is a potential load spike. When many requests miss the same cache entry at the same time, they can all hit the database…

3 min read · Aug 2026Open →
System DesignSD-06

Rate limiter

Every request is a potential abuse point. Make the rate limit check cheap, and the system stays responsive even when traffic spikes.

2 min read · Aug 2026Open →
system-designSD-07

Postman Testing

Keep the hot keys in memory and out of the critical path.

1 min read · Aug 2026Open →

Got an AI ticket that needs an owner?

Send the problem, the constraint and the deadline — you'll get an honest answer on fit within two days.

Copied to clipboard

aniket.umbc@gmail.com

GitHubLinkedIn