I help businesses automate the busywork, make sense of their data, and stand up the tools they actually need — from reporting pipelines and dashboards to full web applications.
01 / Experience
Kisah · Kolkata · On-site
ACEplus · Derek O'Brien & Associates · Kolkata · Hybrid
Mandrake Tech · Pune
Willwali · Remote · Kuala Lumpur
FLAME Sports · FLAME University, Pune
02 / Selected work
Things I've built end-to-end — research systems, full-stack platforms, and delivered client tools. Click any card to open the full case study.
Multimodal Music Emotion Analysis
Graduation research project. A segment-level emotion recognition system that jointly models audio spectrograms and lyrics to track how a song's emotional character evolves over time — deployed as a full Flask web application with recommendations.
Generative AI Football Scouting Platform
Full-stack NLP platform for professional football analytics. Plain-language queries via NL2SQL, chain-of-thought AI scouting reports, ML player profiling with PCA and Random Forest, and four agentic capabilities — all over a 370 MB football database.
Client Work · FLAME Centre for Digital Learning
A delivered analytics dashboard turning raw usage data into decisions for FLAME University.
Earlier work
Additional academic and research projects.
RoBERTa + 26 AMR Semantic Features
A hybrid NLP classifier combining RoBERTa transformer embeddings with 26 hand-engineered Abstract Meaning Representation features. Outperforms pure-transformer baselines by ~18 percentage points on FakeNewsNet (23,196 articles).
ResNet-18 + DistilRoBERTa · Gated Fusion
4-quadrant emotion classifier using gated late-fusion of ResNet-18 audio encoding with DistilRoBERTa lyric encoding. The sigmoid gate dynamically weights each modality per sample — Q2 (Angry) F1 = 0.91.
03 / About
I'm an IT consultant and builder — right now that means running production automation and analytics work at Kisah, alongside select consulting and freelance projects. I came out of FLAME University in 2026 with a CS + Business Analytics degree, but at this point that's the foundation, not the headline — the actual story is building systems that make a business run better.
I've spent the last few years building things — ML research systems, production analytics pipelines, client dashboards, and now full consulting engagements — and the part that keeps pulling me forward isn't the technology itself. It's the moment when something opaque becomes clear: a cohort analysis that shifts a product decision, a dashboard that turns hours of Excel work into seconds, a model that surfaces a pattern nobody had formalised before.
I use AI the way I use any other tool — to get to that moment faster and more reliably. I'm comfortable in the research layer when that's what the problem needs, and equally comfortable in the analytics or product layer when that's what actually moves things forward.
What matters most to me is whether the problem is real and whether the work moves something forward.
The Kisah pipeline runs daily on its own — scraping, transforming, and feeding a live Power BI dashboard without me touching it. MoodTrack and ScoutAI carry the same instinct into research: a Flask app and a full-stack platform, not a results table sitting in a notebook. If it doesn't run on its own, it doesn't count.
CS + Business Analytics means I treat data as an input to decisions, not an output to report. The 2× cohort finding at ACEplus mattered because it changed product strategy — the ranking dashboards I build at Kisah run on the same logic today.
The client-side Moodle dashboard shipped in weeks because building local-first removed IT approval and privacy objections in one move.
I move across NLP research, backend engineering, workflow automation, and client consulting. The common thread isn't the stack — it's understanding the problem well enough to know what actually needs to be built.
Liam Shaw
FLAME University, Pune
CS + Business Analytics · 2026
Education
FLAME University, Pune
La Martiniere for Boys, Kolkata
Technical range
ML & Deep Learning
PyTorch, scikit-learn, CNN-BiLSTM, ResNet-18, XGBoost, PCA, KMeans, Random Forest
NLP & Transformers
RoBERTa, DistilBERT, HuggingFace, NL2SQL, RAG, AMR Parsing, Semantic Search
Languages
Python, Java, JavaScript, SQL, C++, HTML/CSS
Frameworks & Infrastructure
FastAPI, Flask, Spring Boot, React, Next.js, Docker, Node.js, SQLAlchemy
Analytics & CRM
CleverTap, Cohort Analysis, Funnel Analysis, pandas, NumPy, Matplotlib, FuzzyWuzzy, Excel, Power BI, DAX
Automation & Scraping
Selenium, undetected-chromedriver, GitHub Actions, Google Sheets API (gspread)
Tools & Platforms
Git, Jira, SQLite, PostgreSQL, Bubble.io, Jupyter, HuggingFace Hub
04 / Contact
I take on select consulting, freelance, and web application projects — currently alongside a full-time role at Kisah. If there's a real problem you're trying to solve, let's figure it out.
© 2026 Liam Shaw · liamshaw.in
Next.js · Tailwind · Framer Motion