Available for opportunities

Hi, I'm Jayant Singh

|

  • Noida, India
  • 8+ Years Experience
  • Open to opportunities
Download CV Get In Touch View Work
0+
Years Exp
0
Companies
0+
Projects
0+
Technologies
JS

01 About

End-to-end ownership, from data to deployed product.

I'm an engineer who likes the whole path: data processing, model design, API development, and the frontend that finally makes it useful. That range is the point — I can take a problem from "we think something's wrong with this data" all the way to a dashboard someone checks every morning.

Right now that means an AI-powered Data Integrity Engine: a 4-algorithm anomaly detection ensemble, an autonomous agent that performs root-cause analysis, and a 6-step pipeline that replaced work people used to do by hand. Before AI took over my time, I spent years on backend systems in PHP, Laravel, and .NET microservices — architecture, standards, and the unglamorous reliability work that keeps things running.

On the side I build Praxis924, a live AI skill-practice platform I designed, wrote, and deployed alone — RAG grounding on pgvector, multi-provider LLM failover, durable generation workflows, and real-time messaging, running on AWS behind my own CI/CD.

I'm based in Noida, India, and I default to automation over repetition.

◈

End-to-end ownership

Design → deploy, no handoff gaps

◆

AI architecture

Systems & integration, not demos

▲

Automation-first

If it repeats, it gets scripted

●

Backend + ML

The combination is the edge

02 Skills

The toolkit.

Grouped by what I actually reach for, not by how long the list can get.

AI & Machine Learning

  • Google ADK
  • Gemini
  • Groq
  • Hugging Face
  • LiteLLM
  • RAG
  • Vector search
  • Embeddings
  • Prompt Engineering
  • Agentic systems
  • LLM failover
  • Isolation Forest
  • Z-score
  • IQR
  • STL
  • ML pipelines

Backend

  • Python 3.14
  • FastAPI
  • SQLAlchemy
  • Pydantic
  • Alembic
  • REST APIs
  • WebSockets
  • SSE streaming
  • Redis
  • DBOS
  • Caching
  • Connection pooling
  • Pub/sub
  • Microservices
  • Background jobs
  • pytest

Frontend

  • Next.js 15
  • React 19
  • TypeScript
  • Tailwind
  • Zustand
  • Monaco
  • Angular
  • RxJS
  • Chart.js
  • JavaScript
  • HTML5
  • Vue.js
  • UX design

Cloud & DevOps

  • AWS EC2
  • AWS RDS
  • AWS Lambda
  • Secrets Manager
  • Docker
  • Docker Compose
  • Nginx
  • Let's Encrypt
  • GitHub Actions
  • CI/CD
  • LAMP stack

Data

  • PostgreSQL
  • pgvector
  • MySQL
  • AWS RDS
  • Redis
  • Playwright
  • BeautifulSoup
  • Web scraping
  • Data validation
  • Chunking & embedding

Also in the belt

  • C#
  • ASP.NET
  • PHP
  • Laravel
  • CodeIgniter
  • MVC
  • OOP patterns
  • TDD
  • Unit testing
  • Git
  • Drupal
  • WordPress
  • Security

03 Experience

Where I've done the work.

  1. 08/2021 — Present Current

    Software Engineer 2 / ShortHills AI

    Acting as AI Product Engineer & Backend Lead

    • Designed and built a production-grade anomaly detection system using a 4-algorithm ensemble (Isolation Forest, Z-score, IQR, STL).
    • Developed an autonomous AI agent (Google ADK + Gemini) with 10 tools for root-cause analysis.
    • Built a 6-step automated pipeline replacing manual workflows: scraping → validation → detection → reporting.
    • Implemented real-time streaming APIs (SSE) for AI responses.
    • Integrated Playwright-based scraping for multi-source data ingestion (J2, J3 platforms).
    • Designed thread-safe caching and SQLAlchemy connection pooling for scalable backend performance.
    • Built an Angular frontend with real-time dashboards and an AI chat interface.
    • Set up CI/CD with GitHub Actions and AWS-based environment configuration.

    FastAPIPythonGoogle ADKGeminiAngularAWSDocker

  2. 08/2018 — 04/2021

    Software Developer / Chetu India Pvt. Ltd.

    Noida, India

    • Oversaw a team of developers — architecture design, coding standards, and development paths.
    • Worked on backend systems across PHP, Laravel, and .NET microservices.
    • Contributed to WhatsApp API integration and CQRS-based system design.
    • Migrated legacy systems to AWS Lambda with improved performance and scalability.
    • Implemented unit testing and improved system reliability.
    • Collaborated with QA and DevOps teams on production deployments.

    PHPLaravel.NETCQRSAWS Lambda

  3. 04/2018 — 04/2020

    Web Developer / Trivialworks Solutions

    Lucknow, India

    • Built a full crowdfunding web application from scratch using Laravel and CodeIgniter.
    • Integrated PayPal and Authorize.net payment gateways for secure transactions.
    • Implemented a subscription module with PayPal for recurring donations.
    • Integrated Google Location and Kroger APIs for store search and product donations.
    • Managed end-to-end development across cross-functional teams.

    LaravelCodeIgniterPayPalAuthorize.net

  4. 04/2018 — 04/2020

    PHP Developer / Pamac Finserve Pvt. Ltd.

    Pune, India

    • Worked on a support project using CodeIgniter, MySQL, JavaScript, and jQuery.
    • Resolved assigned tickets, maintaining both code and database.
    • Built sample projects with CodeIgniter, Laravel, and Core PHP; used Git for version control.

    CodeIgniterMySQLjQueryGit

04 Projects

Selected work.

The systems I've designed and shipped.

Live Solo project · Jun 2026 — Present

Praxis924 — AI-Powered Skill-Practice Platform

Visit praxis924.com

A full-stack learning platform I built and shipped alone. Admins define a Technology → Framework → Lesson syllabus, and an LLM pipeline auto-generates each lesson — four structured sections plus graded exercises — with a self-review loop that re-scores and improves any section falling below threshold.

  • RAG grounding layer — datasets are chunked, embedded via Hugging Face, and stored in pgvector; retrieval uses cosine similarity with keyword and first-N fallbacks, so generation stays grounded even when vector search misses.
  • Multi-provider LLM failover — Groq → Gemini → Hugging Face with automatic failover, Redis caching, and deterministic offline fallbacks. A single provider outage never breaks generation, chat, grading, or interviews.
  • Durable generation — DBOS Postgres-backed workflows mean a mid-pipeline failure leaves a lesson safely re-runnable instead of half-written, plus a token-frugal "fill gaps" path (0 LLM calls when complete).
  • Real-time messaging — WebSockets over a Redis pub/sub backplane for cross-worker fan-out: presence, typing indicators, read receipts, heartbeat reconnects. Messages persist even when live delivery is down.

Also shipped: Lucy, an SSE-streaming AI teacher grounded in the lesson you opened it from · AI-graded coding challenges · stateless mock interviews · a Next.js 15 App Router frontend with a Monaco practice workspace and admin console · Docker Compose on AWS EC2 behind Nginx + Let's Encrypt · GitHub Actions CI with Alembic migration-drift detection gating an SSH-based CD pipeline · 25+ pytest suites covering generation, RAG, messaging, and AI-safety behaviour.

FastAPIPython 3.14PostgreSQLpgvectorRedisDBOSNext.js 15React 19TypeScriptDockerAWS EC2Nginx

★ Flagship · ShortHills AI

AI-Powered Data Integrity Engine

The system I lead: an end-to-end platform that detects data anomalies, explains why they happened, and reports on them without a human in the loop. Combines a FastAPI backend, an ML detection layer, and an agentic LLM system for analysis.

FastAPIPythonGoogle ADKGeminiSQLAlchemyMySQLAngular

Machine Learning

4-Algorithm Anomaly Detection Ensemble

Production anomaly detection combining Isolation Forest, Z-score, IQR, and STL — each catching what the others miss, ensembled into a single verdict.

PythonIsolation ForestSTLStatistics

Agentic AI

Autonomous Root-Cause Analysis Agent

An autonomous agent built on Google ADK + Gemini with 10 tools at its disposal. Given an anomaly, it investigates and reports the cause — work that used to require an engineer reading dashboards.

Google ADKGeminiLiteLLMTool use

Automation

6-Step Automated Data Pipeline

Scraping → validation → detection → reporting, fully automated, replacing a manual workflow. Playwright-based ingestion pulls from multiple sources (J2, J3 platforms).

PlaywrightBeautifulSoupBackground jobsPython

Full-stack

Real-Time AI Dashboard & Chat

Angular frontend with live dashboards and an AI chat interface, fed by SSE streaming APIs so responses render token-by-token instead of making people wait.

AngularRxJSChart.jsSSE

Fintech · Trivialworks

Crowdfunding Platform

Built from scratch: campaigns, recurring donations via PayPal subscriptions, and Authorize.net checkout. Google Location and Kroger API integration let donors find stores and donate products directly.

LaravelCodeIgniterPayPalAuthorize.net

Architecture · Chetu

WhatsApp API Integration & CQRS Design

Messaging integration built on a CQRS-based system design, separating read and write paths across .NET microservices.

.NETC#CQRSMicroservices

Cloud · Chetu

Legacy → AWS Lambda Migration

Moved legacy systems onto AWS Lambda, improving performance and scalability while keeping the business running through the transition.

AWS LambdaPHPServerless

05 Education

Foundations.

2017

Bachelor of Technology — Computer Science & Engineering

Krishna Group of Institutions — Kanpur, UP

Coursework in C, ASP.NET, HTML, CSS.

2013

Intermediate — Science

Triveni Kashi Inter College — Unnao, UP

2011

HSC — Science

Triveni Shivmaul Singh K.P Singh Memorial Inter College — Raebareli, UP

06 Contact

Let's build something.

Open to conversations about AI systems, backend architecture, and problems worth automating.

Hiring? Grab the full CV.

Complete experience, skills, and education — PDF, 152 KB.

Download CV View in browser
Email jayantsingh924@gmail.com LinkedIn in/jayantsingh924 GitHub @jayantsingh924 Instagram @jayantsingh924
Location Noida, India