Aaditya/Backend & Applied AI
Building ByteVaultLearning Distributed SystemsAvailable for Backend & Applied AI Engineering Roles

Aditya

Backend & Applied AI Engineer · Node | Go | Python (FastAPI) | Qdrant Vector DB | Redis Streams | PostgreSQL

Building production-focused Backend & Applied AI systems. Creator of ArchadiLM (Multi-Tenant RAG Engine) and ByteVault (Cloud Native Storage Platform).

scroll

Technologies I Work With

Technologies I use professionally and the areas I'm currently exploring to build reliable backend systems.

Backend
GoNode.jsPythonFastAPIExpress
Frontend
ReactNext.jsTypescriptTailwind CSS
Databases
PostgreSQLMongoDBRedis
Cloud & DevOps
DockerLinuxCloudflare R2NginxGithub Actions
Currently Exploring
Currently ExploringSystem DesignGenerative AIEvent Driven ArchitectureMessage Queues

// Featured Work

Production Systems & AI Architecture

High-throughput backend microservices, async event processing, vector engines, and Applied AI systems engineered for scale.

ArchadiLM

Flagship

Enterprise Multi-Tenant RAG & Knowledge Workspace

A high-performance Retrieval-Augmented Generation (RAG) platform designed to index multi-modal knowledge materials (PDFs, VTT/SRT transcripts, ZIP archives, web URLs) with realtime SSE streaming and exact grounded source lineage.

Technologies & Infrastructure

Go (Golang)Python (FastAPI)QdrantPostgreSQLRedis StreamsCloudflare R2DockerOpenAI

System Topology & Data Flow


     User / Web Client (Next.js)
                 │
                 ▼
        Go API Gateway (8081) ──► Magic Byte & Security Validation
                 │
        ┌────────┴────────┐
        ▼                 ▼
   Redis Streams     Python AI Microservice (8000)
 (pipeline:upload)   (HyDE + RRF + Reranker)
        │                 │
        ▼                 ▼
 3-Stage Workers     Qdrant Vector Store (HNSW Index)
(Manifest/Processor)      │
        │                 ▼
        └──────────► PostgreSQL (Metadata & Lineage)
  • Mitigating hallucinations & ensuring strict source-grounded responses across multi-file formats
  • Handling long-running document extraction & embedding without blocking API threads
  • Deduplicating retry chunks during worker retries without corrupting vector indices

Other Production Platforms

Win-Win Marketplace

AI-powered marketplace platform for vehicles, electronics and consumer goods.

Next.jsNode.jsExpressRedisMySQLGemini APIS3
View Project ↗

Multi-tenant Hotel SaaS Builder

A multi-tenant SaaS platform enabling hotels to construct white-labeled websites, handle bookings, and process payments.

Node.jsNext.jsRedisPostgreSQLCloudinary
View Project ↗

Healthosyst Platform

Healthcare management SaaS platform featuring realtime patient tracking, appointment scheduling, and automated notifications.

Node.jsNext.jsRedisMySQLSocket.io
View Project ↗

// System Design & Architecture

How The Systems Are Built

Deep dive into the underlying distributed pipelines, vector retrieval engines, state machines, and security mechanisms.

Multi-Stage RAG & Vector Search (ArchadiLM)

Hypothetical Document Embeddings (HyDE) + Reciprocal Rank Fusion + Reranking

When a user submits a query, it undergoes parallel query expansion (Step-Back + Sub-queries) and HyDE document synthesis. Batch vectors are searched across Qdrant using HNSW indices, merged via Reciprocal Rank Fusion (RRF), re-scored via Cross-Encoder Reranking, and streamed back via SSE with grounded file/timestamp citations.

Interactive Topology Diagram


                              User Query ("How do API routes work?")
                                                 │
                                                 ▼
                                     Go API Gateway (8081)
                                                 │
                        ┌────────────────────────┴────────────────────────┐
                        ▼                                                 ▼
             Query Enhancement (Step-Back)                    HyDE Generation (Hypothetical Doc)
                        │                                                 │
                        └────────────────────────┬────────────────────────┘
                                                 ▼
                                Batch Embeddings (OpenAI API)
                                                 │
                                                 ▼
                               Parallel Search in Qdrant Vector DB
                                                 │
                                                 ▼
                               Reciprocal Rank Fusion (RRF Merge)
                                                 │
                                                 ▼
                               Cross-Encoder Reranking & Deduplication
                                                 │
                                                 ▼
                                 Grounded SSE Stream Response

From IT Support to Backend Engineering

My career started in enterprise IT support and gradually evolved into software engineering. Every step has been driven by curiosity, continuous learning, and building real-world systems.

Graduate Trainee

July 2022

Wipro

Started my professional career in Enterprise IT Support, working on incident management, troubleshooting, production support and system reliability.

Enterprise ITProduction SupportTroubleshootingIncident Management

Transition to Software Development

December 2023

Self Learning

Left IT operations and started learning software development from scratch, focusing on fundamentals before frameworks.

HTMLCSSJavaScriptNode.jsReactNext.js

Full Stack Developer Intern

February 2025

Production Internship

Worked on multiple production applications, shipping features, fixing bugs and maintaining real-world applications deployed using cPanel.

Node.jsExpressReactNext.jsMySQLcPanel

Software Engineer

August 2025

Backend Team

Converted into a full-time Software Engineer and started contributing to backend services, APIs and production systems using Node.js and FastAPI.

Node.jsExpressFastAPIREST APIsBackend

Building ByteVault

Present

Personal Engineering

Outside of work, I'm building ByteVault while learning Go, Distributed Systems, Cloud Infrastructure and Generative AI.

GoByteVaultCloudflare R2DockerDistributed SystemsGenAI

Current Focus

Building for the Next Chapter

Professionally, I contribute to backend systems using Node.js, Express and FastAPI. Personally, I'm investing my time in Go, Distributed Systems, Cloud Infrastructure and building ByteVault — a cloud-native file storage platform designed with scalability and production engineering principles in mind.

Engineering Highlights

Production Applications
Worked on multiple production applications across e-commerce, healthcare and hospitality.
Payments
Integrated Razorpay & Stripe with subscriptions, one-time payments and webhook verification.
Async Processing
Built reliable background jobs using BullMQ and Celery for notifications, image processing and scheduled tasks.
AI Integrations
Developed image analysis pipelines for automated categorization, OCR and metadata extraction.
Authentication
Role-based access control, JWT authentication, session management and permissions.
Deployment
Docker, Linux, Cloudflare R2, Redis, Nginx, Production deployments.

Interested in Backend & Applied AI engineering?
Let's talk.

I'm currently working as a Backend & Applied AI Engineer building production systems with Node.js, FastAPI and modern infrastructure. If you're hiring, collaborating on an interesting project, or just want to discuss distributed systems, I'd love to connect.