I turn hard data problems
into systems that run in production.
I research and build systematic trading strategies and production Machine Learning systems that run end to end, from first-principles research to live deployment. I've run strategies on live capital and shipped Machine Learning at scale, without a team to lean on.
Available for a small number of consulting engagements, selective by design.
Shipped production work across
The same discipline, across domains - every claim links to the work behind it
How I work with teams
Three focused engagements - grounded in live markets, production Machine Learning, and enterprise data.
Quantitative Research & Trading Systems
Systematic strategies that survive out-of-sample - and live capital.
I research, build, and deploy systematic trading strategies end to end - signal research through execution and live monitoring - for options and crypto markets.
Learn more →Production Machine Learning & Data Infrastructure
Models and pipelines that run in production - not just in notebooks.
I turn Machine Learning prototypes into reliable production systems, and restructure fragmented data infrastructure so your team can trust the numbers and act on them.
Learn more →Fractional Data-Science Leadership & Advisory
Solve the right problem before you build the wrong system.
Fractional data-science leadership and independent advisory - I help you frame the problem, design the system, and make the build-vs-buy calls that compound.
Learn more →Selected Work
Proof, not promises - what I built, the constraints, and what changed because of it.
An Overfitting-Resistant Backtesting Framework for Options Strategies
Investment Firm
An execution-aware framework that made overfitting structural to catch rather than a discipline to remember - and that gated which strategies reached live capital.
7 Production Forecasting Models Driving Replenishment & Markdown Decisions for Blue Yonder's Enterprise Retailers (5TB+)
Logistics & Supply Chain (SaaS)
7 production forecasting models deployed on a GCP/TFX/Apache Beam/Dataflow stack processing 5TB+ of live supply-chain data, served to enterprise retail clients through Blue Yonder's SaaS platform by a 15-member team.
Regulatory ETL Across 70+ Mainframe Systems for ANZ's APRA Reporting
Tier-1 Australian Bank
Delivered Python-driven DataStage job generation plus an end-to-end Robot Framework test harness covering all 70+ source systems, cutting development and testing time by 50% and catching data errors at the field level before deployment.
Writing
How I think - walk-forward validation, temporal leakage, and quantitative research in live markets.
The Quantitative Trading Playbook
A practitioner's guide to building systematic trading strategies that hold up out-of-sample - from signal research and backtesting discipline to execution modeling and live deployment.
Read →Feature Engineering: The Skill That Separates Good Models from Bad Ones
A practitioner's guide to feature engineering - the craft of transforming raw data into model-ready representations that capture what actually matters for the prediction task.
Read →The researcher who ships
Chemical engineering at IIT Bombay taught me to ask what breaks before what works. Through enterprise data, production Machine Learning at scale, and live quantitative trading, that's still the lens. I build repeatable, scalable systems with low maintenance - and I can take a problem from first-principles research all the way to a live system, on my own.
Read the full story →Let's talk
A good-fit problem looks like: "we have a strategy, model, or pipeline that works in research but we don't trust it in production." If that's you, get in touch - I respond within a few days.
Describe your problem
The most useful first message: what you're trying to do, what you've tried, and the constraint that's biting. This opens a short email template.
Email meBook a call
Prefer to talk? Grab a slot - 20–30 minutes to frame the problem and figure out whether it's a fit. No pitch.
Book a callConnect on LinkedIn
Lower-friction for a first message - we can move it to email or a call if it's serious.
Message on LinkedInHosting an event on quant finance, Machine Learning systems, or data engineering? I'm open to speaking - send an invite.