Shounak Pattewale · AI Engineer

Based in London
Building for the real world

AI Engineer

Currently a Founding Engineer

LLM applications
Memory systems & evaluation

ShounakPattewale

Engineering systems.
Investigating intelligence.

↘Open to opportunities
// Current focus

Currently a Founding Engineer

Pinta B2B
and ScanTrack

// Early-stage startup · London / Remote

Building Pinta Logistic B2B and ScanTrack for an early-stage startup. I own the engineering end to end, from system architecture and backend services to user interfaces and cloud deployment, working remotely from London.

~/pinta-logistic - bash
$ docker-compose up
[+] Starting auth_service... ok
[+] Starting products_api... ok
[+] Starting celery_worker... ok
[+] Starting redis... ok
[+] Starting nginx... ok
[+] Starting postgres... ok
→ 6 services healthy · 0 errors
// Independent research

Active research · AI & memory

LLM applications
and personal memory

// Independent work alongside my startup role

Alongside my work as a Founding Engineer, I independently build LLM applications and investigate how language models store, retrieve and use personal information. My focus is agent memory, retrieval and evaluation: testing what a system remembers, whether its answers are reliable, and what processing costs it incurs.

Explore the research ↗
independent research
Applications · conversational AI
Memory · structured personal records
Evaluation · correctness and cost
Preprint · Zenodo · November 2026
State correctness ≠ answer reliability
// Background

I build AI systems.
Then test their limits.

AI Engineer in London. Currently a Founding Engineer at an early-stage startup, with independent research in memory, retrieval and LLM evaluation.

Explore my career
01 / BUILD

From idea to application

Voice assistants and LLM applications, backed by Python, APIs and cloud infrastructure.

See the work ↗
02 / INVESTIGATE

Memory that can be tested

Research into personal memory, measuring state correctness, answer reliability and cost separately.

Explore the research ↗
03 / DELIVER

Delivered business systems

Pinta Logistic B2B platform and ScanTrack: delivered services for logistics, warehouse operations and ERP integration.

MSc Big Data Science, QMUL · Distinction · 2024
B.Tech Information Technology with Data Analytics · First Class with Distinction

MSc
Distinction
QMUL · Big Data Science
2+
Years
Pro experience
3
Countries
Systems deployed IN · UK · RU
8.17
B.Tech GPA
3rd Rank · MIT-ADTU
~/about - whoami
$ whoamishounak · london · AI engineer$ cat focus.txt→ LLM applications, memory systems,  retrieval and evaluation$ status→ currently founding engineer→ post-study work visa$

From models to working systems.

AI engineering and research, built on Python, backend and cloud experience.


Hover or focus a topic to select its connections. Tap on touchscreens. Choose All connections to reset.

Skills by area

Python is the central foundation connecting these areas.

AI & research

Prompt Engineering, LLM applications, Agent memory, Retrieval, LLM evaluation, SQLite

Voice applications

Pipecat, Deepgram, WebRTC, Claude API

Backend engineering

Python, JavaScript, React, Flask, FastAPI, MongoDB, PostgreSQL, Redis, Celery, Gunicorn, HTMX, 1C ERP, Hostinger, Scrapy, Boto3, Google OAuth, Toast POS, Bash, C++, SEO

Cloud & infrastructure

Docker, Kubernetes, Nginx, AWS, Cloudflare, Selectel

Data systems

Pandas, Spark, Scala, Big Data, Data Analysis

Machine learning

OpenCV, scikit-learn, Machine Learning, Deep Learning, CNN

AI engineering & research
LLM applicationsAgent memoryRetrievalLLM evaluationPrompt engineeringPipecatDeepgramWebRTCClaude APISQLiteTF-IDF
Languages
PythonJavaScriptC++BashScala
Backend
FlaskFastAPIReactHTMXExpress.jsREST APIsMicroservicesWebhooks
Data
MongoDBPostgreSQLRedisMySQLPandasSparkBig Data
DevOps
DockerKubernetesNginxGunicornAWS EC2AWS S3AWS LambdaHostingerSelectelCertbotCloudflare
Integrations
Toast POS1C ERP APIGoogle OAuthScrapyBoto3OpenCVscikit-learnSEO
ML & Data Science
Machine LearningDeep LearningCNNComputer VisionData AnalysisBig DataPrompt Engineering
// Projects

Pinta Logistic B2B ↗

Full-ownership B2B platform connecting factories, warehouses, and retail buyers. Sole engineer across the entire stack - four-tier role system, Flask/HTMX frontend, FastAPI microservices, Celery + Redis async infra, and Selectel cloud deployment.

FastAPIFlaskHTMXMongoDBPostgreSQLRedisCeleryDockerKubernetes1C ERP API
ScanTrack ↗

Role-based fleet and warehouse management for Pinta Logistics across 11 Russian branches. Drivers scan QR codes, barcodes, and DataMatrix labels - product details load instantly from branch-specific 1C ERP APIs. Backend split into two Gunicorn services with OpenCV image preprocessing.

FlaskMongoDB1C ERP APIOpenCVNginxGunicornDockerSelectel
Hilti Tool Tracking ↗

Predictive maintenance platform for the Hilti SCC Hackathon - a 4-5 month international competition. HTOT collects tool usage data and runs it through a pre-trained ML model to predict service requirements before failure, reducing construction site downtime. Finished First Runner Up representing India.

FlaskPythonPredictive MLscikit-learn
Sign Language Communicator ↗

Real-time ASL recognition using CNN-based image segmentation, comparing ResNet50, VGG16, and MobileNet on live webcam feed. VGG16 achieved 0.99 mAP at 60ms latency. Covers ASL alphabets and salutations - published in IJRESM Vol. 5 No. 6 (2022), co-authored at MIT-ADTU, Pune.

PythonCNNComputer VisionResNet50VGG16MobileNetDeep Learning
Restaurant Multilingual Menu ↗

Pixel-perfect recreation of Angus Steakhouse's designer PDF menus as a multilingual web experience - English, French, Italian, Spanish, Chinese, and Japanese with persistent language memory. Built as an internal pitch to Noble Restaurant Group for transitioning from printed PDFs to a live digital system.

HTMLCSSJavaScriptSVGi18nlocalStorage

// Research and publications


Preprint · Zenodo · November 2026

Validated Personal Memory for Language Models: A Bounded Study of State Correctness, Answer Reliability, and Processing Cost

Shounak Pattewale · Published · Version 1.0

A bounded study of structured personal-memory middleware, examining state correctness, answer reliability and processing cost separately. Published preprint; not peer-reviewed.

Nine methods across three model configurations produced 1,620 answer outputs. All 486 saved state-transition traces matched their references. Separate public-benchmark analyses evaluate models without the middleware.

DOI: 10.5281/zenodo.24210707 · Creative Commons Attribution 4.0

Ongoing exploratory research

Neural Memory and Adaptive Storage

Investigating whether neural networks can store editable facts, support updates and forgetting, and preserve unrelated information. I developed prototypes, training and evaluation workflows, and comparisons with exact-record storage.

NMD002 recorded 126 completed backend runs. None of the tested weight-based backends passed the full evaluation screen; a query adapter passed its synthetic interface screen. These findings support retaining exact records as authoritative storage while exploring neural interfaces.

This earlier work informed the subsequent SQLite-backed personal-memory study. The mechanisms are distinct: no validated replacement for conventional storage or solution to catastrophic forgetting is claimed.

Journal publication · IJRESM · 2022

Comparative Study of CNN-Based Sign Language Translation Models

Co-authored sign-language research published in IJRESM, Volume 5, Issue 6 (2022), during my undergraduate studies and before my MSc. This journal publication is separate from the 2026 personal-memory preprint.

Research timeline

14 November 2026 - Published the personal-memory research preprint on Zenodo.

November 2026 - Prepared the bounded structured-memory study, building on questions raised by the earlier neural-memory experiments.

Earlier experiments - Explored neural-memory storage, updates and forgetting before the structured personal-memory study. Exact start date is not established; this work remains exploratory.

2022 - Published CNN-based sign-language research in IJRESM, before the MSc.

// How I Work

A useful system has to hold up beyond the demo. In production, that means dependable services and maintainable code. In research, it means testing assumptions, examining failures and being clear about what the evidence supports.

- London · Late hours · Coding · Strong Coffee

~/workspace - bash · hosted VPS
$ cat evaluation-principles.txt
State correctness · Answer reliability · Processing cost
Report findings, failures and limitations.

$ ps aux | grep hermes
→ hermes_agent   running · 193 days uptime · 0 crashes
// Career timeline

Professional experience, education and earlier technical internships.

JUN 2025 - PRESENT
Early-Stage Startup · London / Remote · Employment
Founding Engineer

Own full-stack client delivery from discovery and technical planning through architecture, implementation, deployment and support. Build Python/FastAPI services, PostgreSQL-backed systems and React/TypeScript interfaces; manage Linux-hosted Docker infrastructure. Build and evaluate AI-enabled features and retrieval workflows with attention to reliability, latency and cost.

PythonFastAPIReactTypeScriptPostgreSQLDockerClient delivery
2024
Queen Mary University of London · Education
MSc Big Data Science - Distinction

Graduated with Distinction. Studied large-scale data processing, machine learning and statistical modelling.

Big DataMachine LearningData Science
AUG 2022 - JUL 2023
TechStax · Previous employer
Full-Stack Python Developer

Developed Flask services and integration pipelines connecting CloudKitchens/Hubster with Toast, Lightspeed and other external platforms. Built and debugged REST APIs, webhooks, authentication and data mappings; investigated production integration failures and collaborated on fixes. Worked with databases, testing and Git-based delivery.

PythonFlaskREST APIsWebhooksIntegrations
2022
MIT ADT University · Education
B.Tech Information Technology / Data Analytics

First Class with Distinction. GPA 8.17/10; third rank.

Data AnalyticsPythonMachine Learning
JUN 2021 - OCT 2021
Drapezy · Previous employer
Backend Developer

Developed backend functionality and API/database logic for an early-stage product, collaborating in a fast-moving startup environment.

Backend developmentAPIsDatabases
JAN 2021 - APR 2021
NDB Inc. · Internship
Backend Web Development Intern

Built and maintained backend API functionality with Node.js and MongoDB, collaborating through Git-based development workflows.

Node.jsMongoDBGit
NOV 2020 - MAY 2021
SoftTech Data Securities · Internship
Machine Learning Intern

Worked on media morphing detection using Python, computer vision and classification models for manipulated-content analysis.

PythonMachine LearningComputer Vision
// Contact

★ London · Open to opportunities

Get in touch

Get in touch about AI engineering roles, client projects or research. My focus is LLM applications, memory systems, retrieval and evaluation, backed by Python and cloud engineering experience.

Your message is delivered securely through Web3Forms.

Shounak Pattewale · London · 2026

YOUR CHOICES

Privacy & cookies

Choose what you share. The website works with optional analytics switched off.

Necessary

Always on

Remembers your cookie choices for 180 days. No tracking.

Helps understand page visits, how visitors find the site and broad device types. Only collected with your permission and kept for up to 90 days. The analytics cookie expires after 30 minutes without another page visit.

No advertising or personal profiles

Analytics does not store your name, email, form contents, precise location or full IP address.

You stay in control

Change your choice here at any time. Switching analytics off stops future tracking and removes its cookie. For access or deletion of previously collected data, use the contact form.

About this policy

This portfolio is operated by Shounak Pattewale. Hosting services may keep security logs. Fonts are served directly from this website. Linked websites have their own privacy policies. Submitting the contact form sends your name, email and message through Web3Forms so Shounak can reply. These details are not included in website analytics.