3D Mode
Amanpreet Singh AmanX
Recruiter Mode
Open to Full-Time Roles & High-Impact Engineering
Hoshiarpur, Punjab, India

Architecting Production AI Systems & Real-Time Edge Intelligence.

Focusing on: AI Systems Engineer |

Hi, I'm Amanpreet Singh (AmanX) — Applied ML Engineer (NeuroMl.ai alum, PTU). I build production-grade Generative AI applications (such as AI Astro on Google Play), enterprise RAG platforms with automated hallucination evaluation, and 100% on-device local voice pipelines combining Whisper, quantized LLMs (llama.cpp), and ONNX speech synthesis.

Recruiter Fast-Track (30s) Explore Shipped Work LinkedIn Profile GitHub (@AmxnCode)
40+ Public Repos & AI Tools
Google Play Shipped App (AI Astro)
P2P Audio Real-Time Sync (AI Music Player)
< 1.0s Local Edge Voice Latency
HR & Hiring Manager Quick-Deck

Candidate Snapshot & Core Superpowers

LinkedIn Hire Amanpreet

Applied AI & ML Track Record

Experience developing machine learning systems at NeuroMl.ai pvt ltd (2020–2023) and degree from Punjab Technical University. Bridges cutting-edge models with production code.

Edge & Local Voice AI Pioneer

Engineered end-to-end local speech-to-speech pipelines for Python and Android. Combines Faster-Whisper, quantized LFM (350M Q4_0), and ONNX Supertonic TTS for zero-cloud latency and complete privacy.

Shipped Consumer AI Products

Built and launched AI Astro on Google Play Store (astrological AI synthesis) and developed the AI Music Player with voice commands and low-latency P2P music sync.

Work Preferences & Availability

Status: Immediate availability for Full-Time roles & High-Impact Contracts.
Location: Hoshiarpur, Punjab, India (Open to Remote Worldwide / Hybrid / Relocation).
Roles: AI Systems Engineer, GenAI Developer, ML Engineer.

Verified Profile

Career Experience & Education

Professional background pulled directly from my LinkedIn profile.

Professional Experience

NeuroMl.ai pvt ltd

2020 – 2023 India

Focused on applied machine learning architectures, neural models, vector embeddings, and production AI system engineering. Developed algorithms for automated intelligence processing and scalable backend integration.

View NeuroMl.ai on LinkedIn
Formal Education

Punjab Technical University

2015 – 2018 Punjab, India

Built foundational principles in computer science, software engineering, algorithms, data structures, and computer architectures, paving the path into applied deep learning and software systems.

View PTU on LinkedIn
Upwork & Client Portfolio

Featured Projects & Shipped Deliverables

Proven client-grade engineering — from published consumer mobile AI apps on Google Play Store to live production SaaS platforms, autonomous AI agents, and Model Context Protocol (MCP) servers.

Up

Ready for Upwork Contracts & Bespoke AI Development

Available for Fixed-Price Milestones or Weekly Hourly contracts. Guaranteed escrow-protected milestones, production-ready deployments, full IP ownership transfer, and clear architectural documentation.

Hire for Your Project
Live SaaS & MCP Production Live

OneAIMemory — Encrypted Memory Layer for AI Coding Agents

Client Deliverable: Shipped zero-knowledge AES-256-GCM memory layer connecting Claude Desktop, Cursor, and ChatGPT to live IDE & browser context via 5 native Model Context Protocol (MCP) tools.

Lightweight macOS companion app that captures active browser tabs, search terms, code file edits, and active project context on-device. Encrypts all payloads locally before storing them in partitioned database envelopes for seamless AI agent context injection.

Zero-Knowledge Architecture
Mac On-Device Capture → AES-256-GCM Encryption → Partitioned Postgres → MCP Context Gateway (< 100ms)
  • TypeScript
  • Next.js
  • Model Context Protocol (MCP)
  • AES-256-GCM
  • scrypt KDF
  • PostgreSQL
  • OAuth PKCE
Visit oneaimemory.com
AI Desktop OS & Voice Production Live

NodeOS AI — AI Desktop Workspace for Voice, Chat & Automations

Client Deliverable: Full-stack AI workspace platform featuring visual workflow automations and 100% on-device speech-to-speech conversational agents with sub-500ms voice response times.

Brings real-time AI conversational voice and desktop workflow automations into a unified interface. Combines in-browser Moonshine WASM speech recognition, Silero VAD turn detection, local Qwen/llama.cpp inference, and Piper streaming sentence-by-sentence TTS.

Sub-500ms Voice Pipeline Flow
Mic Stream → Moonshine WASM STT + Silero VAD → Streaming llama.cpp → Piper Worker TTS → Audio Speaker
  • Next.js
  • llama.cpp (Qwen)
  • Moonshine WASM STT
  • Silero VAD
  • Piper TTS
  • Express.js
  • Supabase
  • Stripe Billing
Visit nodeosai.com
Google Play Published Live Consumer App

AI Astro — Generative Birth Chart & Horoscope App

Client Deliverable: Shipped consumer Android application on Google Play Store featuring exact astronomical ephemeris calculations and personalized generative AI birth chart interpretations.

Calculates precise celestial planetary coordinates based on user birth coordinates and fuses this with modern generative narrative models to deliver personalized personality breakdowns, career forecasts, and daily life insights.

Core System Capabilities
User Birth Coordinates → Astronomical Planetary Ephemeris → Generative AI Synthesis → Personalized Astrological Reports
  • Android Kotlin
  • Generative AI
  • Astronomical Calculations
  • Responsive Mobile UI
  • Google Play Store
  • AdMob SDK
Google Play Store
Google Play Published Real-Time P2P

AI Music Player — Voice Commands & P2P Sync

Client Deliverable: Shipped Android mobile music streaming platform featuring voice-controlled playback and low-latency peer-to-peer (P2P) synchronized music sharing.

Allows users to control audio playback with hands-free natural voice commands and listen to music together with remote friends in exact real-time synchronization over peer-to-peer sockets.

Core System Capabilities
Voice Intent Recognition → Track Parser → Low-Latency P2P Socket Sync → Sub-Millisecond Multi-Device Audio
  • Android Kotlin
  • Speech Recognition
  • Peer-to-Peer (P2P)
  • Audio Engine
  • Real-Time Socket Sync
  • Google Play Store
Google Play Store
Google Play Published Live Consumer App

AI Content Writer — Multi-Template & SEO Writing Suite

Client Deliverable: Shipped production writing assistant on Google Play Store featuring structured multi-stage SEO article generation, copywriting templates, and local draft persistence.

Production Android app providing multi-stage SEO article synthesis, social captions, sales emails, and blog posts with section-by-section regeneration, Google Mobile Ads SDK integration, and privacy compliance.

Multi-Stage Generation Flow
Content Brief & Keywords → Multi-Stage Section Plan → Contextual LLM Drafting → Section-by-Section Regeneration & Export
  • Android Kotlin
  • LLM Prompt Engineering
  • SEO Outline Generator
  • Mobile Ads SDK 25.4
  • Google Play Store
Google Play Store
Google Play Published Multimodal Suite

All AI Tool — Multimodal Productivity & Focus App

Client Deliverable: Shipped mobile & desktop workspace application integrating screenshot OCR vision classification, Whisper voice memo transcription, and developer focus timers.

All-in-one productivity assistant built for engineers and founders: captures voice notes with Whisper, automatically categorizes screen snippets via vision models, and manages deep-work state machines.

Core Capabilities Flow
Voice Notes / Screen Snapshots → Whisper Transcription + Vision Classifier → Task State Machine → Productivity Analytics
  • TypeScript
  • React / Android
  • Whisper Audio
  • Vision Models
  • Google Play Store
Google Play Store GitHub Repo
Autonomous AI Agents Open-Source System

Marketing Agent — Autonomous Digital Marketing Employee

Client Deliverable: Autonomous marketing system in Electron & Next.js that pulls live analytics, detects keyword opportunities with real volume, generates channel drafts, and handles compliance checks.

Acts as a virtual digital marketing employee: pulls real numbers from Google Analytics (GA4), Search Console, and social accounts via Composio; crawls competitor sitemaps for keyword gaps; drafts channel-specific content; runs automated claims verification; and publishes automatically.

Agent Loop Flow
Account Telemetry (GSC/GA4/Social) → Suggestion Engine → Multi-Channel Brief → Automated Claims Check → One-Click Publishing
  • Next.js 15
  • Electron
  • SQLite (Drizzle)
  • Composio OAuth
  • Ollama / OpenRouter
  • Multi-Agent Loop
GitHub Repository
Model Context Protocol • IoT Open Source

IoT-MCP-Servers — Model Context Protocol Bridge for Smart Hardware

Client Deliverable: Standard Model Context Protocol (MCP) server architecture bridging LLMs (Claude, Cursor, custom agents) directly to physical IoT hardware and smart home automation.

Enables autonomous AI models to read real-time sensor telemetry, control smart home devices, interface with microcontrollers (ESP32, Raspberry Pi, Arduino), and trigger automation actions over MQTT, WebSockets, and standard MCP protocol tools.

MCP Hardware Architecture
LLM / AI Agent (Claude, Cursor) → Model Context Protocol (MCP) → IoT Server Bridge → Hardware Sensors, ESP32 / MQTT Microcontrollers
  • TypeScript
  • Python
  • Model Context Protocol (MCP)
  • MQTT Protocol
  • ESP32 / Microcontrollers
  • Hardware Telemetry
GitHub Repository
Interactive Recruiter Bot

Ask Aman's AI Assistant

Have questions about my technical background, architecture decisions, or role fit? Ask directly or click any pre-configured question below!

AmanX Interactive Candidate Bot ● Online
Model: Local Knowledgebase
Hello! I am Aman's interactive assistant. I can answer technical inquiries about his work at NeuroMl.ai, his published AI Astro app on Google Play, his 100% on-device voice pipelines, and his enterprise RAG architectures. Feel free to ask a question or select from the options below!
Core Competencies

Skills & Engineering Disciplines

Proficiencies honed across production AI platforms, real-time edge pipelines, and full-stack software development.

LLM Systems & RAG

Designing reliable agentic systems and multi-hop retrieval pipelines with strict hallucination guardrails.

Multi-Agent RAG LLM-as-a-Judge Vector DBs (Pinecone/Chroma) Dense Embeddings Fine-Tuning (LoRA) LLaMA-Factory Prompt Engineering OpenRouter Fallback

Edge AI & Audio Pipelines

Deploying quantized models directly on local consumer hardware for sub-second, zero-cloud performance.

faster-whisper llama.cpp ONNX Runtime Supertonic TTS 4-bit Quantization (Q4_0) CTranslate2 Android NDK / JNI Streaming Audio

Backend & Scalable Systems

Robust microservices, async APIs, automated browser scraping, and resilient containerization.

Python (AsyncIO) FastAPI Docker & Compose Playwright Headless RESTful APIs WebSockets Git / GitHub Actions Linux / macOS CLI

Modern Frontend & Mobile

Responsive, accessible user interfaces with clean architecture and reactive state management.

TypeScript Three.js (WebGL) Next.js (App Router) React Tailwind CSS Android (Kotlin) State Management Interactive Dashboards
Available Immediately

Let's Build Something Extraordinary

I am actively looking for high-impact AI Engineering, Full-Stack GenAI, and Machine Learning roles. Whether you have an immediate hiring need or want to discuss an innovative architecture, I'd love to connect.

Send Email Direct
Copied to clipboard!