Available for work

Hi, I'm Prakriti

>

United States

I build full-stack products and the GenAI systems behind them — from LLM pipelines that turn messy enterprise data into decisions, to the APIs and dashboards people actually use.

View My Work
Get in Touch
Resume
GitHub
LinkedIn
Email
01 / About

Build it, ship it, keep it running.

I'm a software engineer working at the intersection of generative AI and full-stack development. I'm currently building LLM-powered tooling at John Cockerill Industries — pipelines that turn scattered SAP, SharePoint, and Teams data into cost estimates and recommendations sales teams can act on the same day.

Before this I spent two years at Cashfree Payments, where I built risk and fraud APIs in Java and Go that ran inline in production, shipped RESTful services with React/TypeScript dashboards on top, and led a cross-functional team of 10 through a React Native app launch. I also hold a Master's from Illinois Institute of Technology, where I did systems research on Kafka-based event streaming and distributed coordination.

My stack spans Java, Python, and Go on the backend to React and Next.js up front, with AWS, GCP, Docker, and Kubernetes tying it together — and lately a lot of LangChain, RAG pipelines, and prompt engineering, since GenAI is the main thing I build now.

Outside of work I care about shipping things that are technically solid and genuinely useful, not just impressive on paper.

2+Years of Experience
60%Manual Work Automated
700+Automated Tests / Day
7%Product Revenue Contributed
Prakriti Sharma

Prakriti Sharma

Software Engineer · GenAI · Full-Stack

United States
prakritimksharma@gmail.com
PythonJavaReactLangChainAWS
Software Engineer·GenAI·Full-Stack·Backend·United States·
02 / Deploy History

Where I've been on call.

  1. ▸ MAR 2026 → PRESENT · REMOTE

    GenAI Software Engineer

    John Cockerill Industries

    • Built an LLM-powered spare-parts cost estimation system, reducing manual quote preparation time by ~60% by mining SAP, SharePoint, and Teams purchasing data with Python, LangChain, and the OpenAI/Gemini APIs.
    • Improved aftermarket pricing accuracy by ~30% by developing an LLM-assisted historical cost modeling pipeline using Python, Scikit-learn, Pandas, and SAP data extraction scripts.
    • Accelerated same-day quote generation for sales teams by building an AI-driven data retrieval and recommendation API and React dashboard, using FastAPI/Node.js, Python, LangChain, PostgreSQL, and LLM embeddings.
    PythonLangChainFastAPIReactPostgreSQLOpenAI

  2. ▸ SEP 2022 → JUL 2024 · BENGALURU, INDIA

    Software Engineer

    Cashfree Payments

    • Engineered multi-level risk blacklisting and whitelisting APIs in Java and Go, expanding system coverage and contributing 7% of product revenue within 5 months.
    • Designed and deployed Success Rate RESTful APIs with ReactJS/TypeScript dashboards, improving transaction visibility and driving 15% revenue growth over 2 quarters.
    • Refactored Java payment gateway modules with zero downtime and wrote Python automation scripts covering 100% of regression testing, improving release velocity.
    • Integrated commonauthsvc into CI/CD pipelines using Jenkins, automating 700+ test cases/day.
    • Built 3 levels of blacklisting APIs in Java, expanding the team's scope by up to 25%.
    • Led a cross-functional team of 10 to deliver a React Native cross-platform app, increasing customer engagement by 40% in 6 months.
    • Developed RESTful APIs for Aggregation Rules in Java and ran performance testing with JMeter, boosting AutoCollect revenue by 9.8% and Cashgram by 17.6%.
    • Achieved 100% automation coverage using Appium integrated with BrowserStack for cross-platform testing.
    JavaGoReactTypeScriptJenkinsJMeter

  3. ▸ OCT 2024 → OCT 2025 · CHICAGO, IL

    Graduate Student Researcher

    Illinois Institute of Technology

    • Developed robust prototypes addressing server consistency challenges, using Kafka for event streaming and Zookeeper for distributed coordination, resolving 78% of major system crashes.
    KafkaZookeeper
03 / Training Data

Where I studied.

▸ AUG 2024 → MAY 2026 · CHICAGO, IL

Illinois Institute of Technology

Master of Science in Computer Science

/ 4.0

tag: ms-cs · 2026

▸ JUN 2019 → JUL 2023 · CHENNAI, INDIA

Vellore Institute of Technology

Bachelor of Technology in Computer Science Engineering

/ 10.0

tag: btech-cse · 2023

04 / The Stack

The stack I reach for.

Languages(9)

82%
JavaPythonJavaScriptTypeScriptGoC#C++HTML5CSS3

Frontend & Backend(10)

75%
ReactNode.jsNext.jsAngularVue.jsExpress.jsSpring Boot.NET CoreDjangoFastAPI

Cloud & DevOps(6)

74%
AWSGCPDockerKubernetesJenkinsKafka

Databases & Data(6)

71%
MySQLPostgreSQLMongoDBDynamoDBElasticsearchGraphQL

AI / GenAI(10)

78%
LangChainOpenAI APIGeminiHugging FacePandasScikit-learnRAGPrompt EngineeringNLPVector Search

Testing & QA(3)

70%
JMeterAppiumBrowserStack
$ gh stats --user prakriti31 --live
Public Repos53
GitHub Stars9
Followers10
Top LanguagesJava · JavaScript · Python
04 / Shipped

Featured Projects

Sludge-RAG — Organizational Context Layer for RAG screenshot

01 / 06

Sludge-RAG — Organizational Context Layer for RAG

A RAG system that surfaces not just what a policy says, but why it exists. Sludge-RAG mines the Slack threads and email chains around a document, runs a multi-turn Claude pipeline to extract the organizational rationale behind each decision, and attaches it as metadata to every indexed chunk — so a query like "why is retention 90 days" comes back with the GDPR and audit context, not just a dry PDF excerpt. A dual-pane "Vibe-Check" playground puts plain vector search side by side with rationale-augmented search so the difference is visible, not just claimed.

Next.jsFastAPIPythonDockerWeaviate
View Build
AgentHub — Terminal-First Coding Agent Manager screenshot

02 / 06

AgentHub — Terminal-First Coding Agent Manager

A SaaS dashboard for developers running multiple AI coding agents — Claude Code, Copilot, Cursor, Codex — in one place instead of juggling terminals and logs. Tracks sessions per agent with token counts, cost, duration, and status, streams a terminal-style activity log, and pushes Slack and email alerts when a session finishes or fails. Auth is JWT plus Google OAuth with per-user @alias handles for team visibility, rate-limited and request-logged on the backend.

Node.jsExpress.jsSlackGoogleJWT
View Build
TrackSplitAI — Multi-Tenant Expense Splitting SaaS screenshot

03 / 06

TrackSplitAI — Multi-Tenant Expense Splitting SaaS

A multi-tenant expense tracking and splitting SaaS with AI categorization, a conversational assistant, and real subscription billing — not a toy CRUD app. Seven FastAPI microservices talk over a RabbitMQ event bus with dead-letter queues and per-consumer dedup, Gemini categorizes expenses and answers questions, and Stripe Checkout handles billing with signature-verified, idempotent webhooks. Runs on Kubernetes (EKS) via Terraform-provisioned infra, autoscales on CPU and queue depth, and ships through a GitHub Actions pipeline with coverage gates, Trivy scanning, and Prometheus/Grafana/Loki observability.

ReactFastAPIMongoDBRabbitMQKubernetesStripe
View Build
Instagram Analytics — Real-Time Scraping Pipeline screenshot

04 / 06

Instagram Analytics — Real-Time Scraping Pipeline

An Instagram analytics pipeline that scrapes profiles via Apify, queues the work through Kafka, and pushes results to a React dashboard over WebSockets in real time. FastAPI handles the API layer, a Python consumer service does the actual scraping and writes to MongoDB or DynamoDB depending on deployment, and rate limiting plus per-query performance logging keep the scraping layer honest at scale.

PythonKafkaReactMongoDBDynamoDB
View Build
ARIA — Adherence Risk Intelligence Agent screenshot

05 / 06

ARIA — Adherence Risk Intelligence Agent

A between-visit clinical intelligence platform for hypertension management that gives clinicians an 8-minute pre-visit briefing instead of a blank chart. Ingests patient data via FHIR R4, then runs a three-layer nightly pipeline — a deterministic rule engine (gap, therapeutic inertia, adherence-BP correlation, deterioration, and variability detectors) feeds a weighted risk score, which feeds a Claude-generated 3-sentence clinical narrative validated against faithfulness and safety guardrails before it's ever shown. Also runs a deterministic drug-interaction checker, a tool-using clinical chatbot, and a patient-facing PWA for home BP submission — all driven by a 30-second poll worker, no Celery, no Redis queue.

PythonFastAPIPostgreSQLReactClaude
View Build
PartSelect Chat Agent screenshot

06 / 06

PartSelect Chat Agent

A scoped AI chat assistant for PartSelect's refrigerator and dishwasher catalog — finds parts by symptom or model number, verifies compatibility against a specific model number (never guesses), and walks customers through installation and troubleshooting with interactive, localStorage-persisted checklists. Built on Claude tool-use for part search, compatibility checks, and order support, with rich inline product cards and hard scope enforcement so it refuses anything outside the parts catalog.

ReactNode.jsExpress.jsClaude
View Build
06 / Research

Things I've published.

▸ IJRAR · 2023

Image Shadow Removal Using Non Shadow Mapping

A shadow removal algorithm that detects shadows and lifts them by matching each shadow region to its most similar non-shadow counterpart, then transferring brightness while preserving texture. Detection combines gradient, texture (Texton), and spatial-distance features from mean-shift segmentation with Y-channel and HSI-space brightness cues clustered via k-means. Removal uses HSV histogram matching between each shadow region and its best-matched non-shadow region, followed by boundary smoothing across the seams. Built and evaluated in MATLAB.

Read Paper Code
Open to Work·Get in Touch·Open to Work·Get in Touch·
07 / Open a Channel

Get in Touch

If you're hiring, building something interesting, or just want to talk GenAI — my inbox is open.

Phone

+1 (312) 479-6193

Email

prakritimksharma@gmail.com

Location

United States

Find me on

prakriti@dev:~/contact