Principal Product Designer · Fintech, Capital Markets & Decision Intelligence

I design interfaces that keep high-stakes decisions from being made on misread data.

Across climate risk, options trading, workforce planning, clinical benchmarking, and talent mapping, the same failure repeats: dense model output is easy to misread, and the consequence lands in capital, risk, headcount, hiring, and decisions that are expensive to reverse.

I build institutional decision-intelligence systems that do not just output an answer, but expose the mechanism behind it, keep uncertainty or topology legible, and make the next action auditable rather than merely confident. I accelerate engineering by using AI coding agents to turn strategy into functional React and TypeScript prototypes, so teams build from working logic, not static specs.

Open to principal/staff product design roles · Greater New York Area

Reveal the mechanism

I design decision interfaces that show what drives the recommendation, which assumptions matter, and where the model stops being certain.

Keep uncertainty visible

I do not flatten probabilistic systems into fake certainty. Range, confidence, and consequence stay legible in the interface.

Support auditable action

The output is not just a screen. It is a decision artifact a portfolio manager, operator, or staffing lead can defend in a real review.

Where Misreading Breaks Decisions

The through-line in this portfolio is not the industry. It is what happens when people misread dense information under pressure. The value proposition is direct: the stakes of misreading data are measured in capital, risk, and decisions that cannot be undone.

Climate Risk

22,000 probabilistic data points can turn into incorrect investment calls. The portfolio solution is to keep uncertainty visible in the interface.

Options Trading

Traders misread the volatility surface and commit capital on the wrong read. The portfolio solution is linked decision geometry across slice, grid, spread, and strategy views.

Workforce Planning

Staffing uncertainty gets flattened into false precision and headcount is misallocated. The portfolio solution is an allocation model that turns uncertainty into actionable moves.

Clinical Benchmarking

Exception patterns are missed and care quality risk stays hidden too long. The portfolio solution is an exception-led command center.

Talent Mapping

Candidates are misread because expertise is treated like a list instead of a network. The portfolio solution is graph navigation that makes expertise topology visible.

Finance Operations

AI-flagged exceptions get rubber-stamped or ignored and audit defensibility erodes. The portfolio solution is a reviewer workspace that keeps model uncertainty visible and welds each verdict to an immutable audit artifact.

Selected Work

Finance Operations · Reg-Tech · AI Exception Review · Compliance Dashboard

Incline Trust

Reviewers attest AI exceptions with an audit artifact that defends the call

A reviewer workspace for an AI-driven corporate spend and payments platform. The model flags expense and vendor exceptions; the interface makes that model legible enough that a controller can accept, adjust, or reject each call under a tunable confidence band, then emit an immutable, auditable record without leaving the page.

AI Trust
Exception Review
Uncertainty Visualization
Material Design 3

View case study →

Capital Markets · Options Trading · Risk Visualization · Decision Intelligence

Volatility Surface

One market context held across 5 linked views, so the desk carries the right trade geometry

A linked decision-intelligence workspace for options traders. It holds one market context across surface, slice, grid, spread, and strategy views, with a stress-calibrated value-at-risk gauge, so the desk reads the field correctly instead of carrying the wrong trade geometry into action.

Trading UX
Decision Geometry
WebGL Surface
Value-at-Risk

View case study →

Climate Risk · TCFD Disclosure · Product Design · Risk Modeling

Uncertainty as Signal – Risk Meter for Climate Data

22,000 climate data points per asset made committee-ready without hiding the uncertainty

A disclosure platform for Tier 1 banks and insurers, wired to live climate models from day one. Turns 22,000 probabilistic climate data points per asset into investment committee-ready risk intelligence, without hiding the uncertainty that would otherwise lead to incorrect capital calls.

Information Architecture
Uncertainty Visualization
Progressive Disclosure
TCFD / ISSB

View case study →

Private Capital · Enterprise Workflow · Archival Reconstruction

North Bridge

Signal triage, context, notes, and follow-ups unified into one coverage workflow

A public-safe reconstruction of a private-capital coverage portal. Rebuilt from archival wireframes and notes, it shows how signal triage, company context, notes, and follow-up tasks work as one connected workflow.

Enterprise UX
Workflow Design
Archival Reconstruction
SAP Fiori

View case study →

Enterprise Intelligence · Information Architecture · Talent Navigation

Know Who Knows

Under 4 min to assemble a qualified team from a 200-person pool

An enterprise talent mapping interface built for a major financial and legal intelligence platform. Roster, Org Grid, and Talent Network views prevent candidate misreads by making the topology of expertise visible across a 200-person pool.

Information Architecture
Graph Navigation
Progressive Disclosure
Talent Graph

View case study →

Healthcare Analytics · Clinical Operations · Data Visualization · Anomaly Detection

What Gets Measured – Clinical Exception Dashboard

101 physicians × 4 years made scannable, so exception patterns surface before they become risk

A clinical performance benchmarking system for 101 physicians across 4 years of data. Rebuilt as an exception-led command center so missed exception patterns become visible before they turn into care quality, equity, or workload risk.

Benchmark Design
Clinical Operations
Parallel Coordinates
D3.js

View case study →

Clinical Informatics · Mobile R&D · Cross-Platform Verification

Decision Logic Before Build

2 critical logic errors caught pre-build, before a native team wrote production code

An iOS and Android clinical mobile prototype sharing one state machine, with divergent platform treatment, built to verify decision logic, accessibility structure, and workflow coverage in Discovery, before a native app team writes a line of production code.

Clinical Informatics
Cross-Platform Prototyping
Accessibility Verification
R&D Methodology

View case study →

Founder-Built Product · Workforce Analytics · Allocation Model · Decision Intelligence

HR as DJ – Staffing Radar

Shipped solo: product, allocation model, and decision layer turning staffing uncertainty into moves

Built and shipped a workforce planning product around a custom allocation model. Designed the interface, the system logic, and the decision layer that turns staffing uncertainty into actionable operating moves instead of misallocated headcount.

Founder
Decision Intelligence
Data Visualization
Allocation Model

View case study →

About

Principal product designer with 12+ years building interfaces where the stakes of misreading data are measured in capital, risk, and decisions that cannot be undone.

I work at the intersection of financial data, institutional decision-making, and complex information systems. I was building data-heavy institutional design systems before “consumer UX” was a category. The common thread is not the domain. It is the user: someone who must make a high-stakes call using a model they did not build, on a timeline they cannot control.

I accelerate engineering by using AI coding agents to turn strategy into functional React and TypeScript prototypes, from risk meters and anomaly dashboards to geospatial climate maps and retrieval-first portfolio shells. I do not just design screens. I hand teams working logic, not static specs. AI-fluent, with Anthropic certifications.

I previously founded Staffing Radar, a workforce analytics application built around a custom mathematical allocation model. I built the product, the model, and the interface, then shipped it. Active in the NYC tech community as a speaker since 2013.

Selected clients and contexts
UBS
Investment Banking · Trading Platforms
Chicago Mercantile Exchange
Derivatives Exchange
Refinitiv
Financial Data & Infrastructure
KKR
Alternative Asset Management
Thomson Reuters
Legal & Financial Intelligence
Google
Design Sprints · DoubleClick for Publishers
Capital-markets client work delivered embedded via EPAM Systems, 2010–2019.

Let’s Talk

Siarhei Mardovich · Greater New York Area · siarhei.mardovich@gmail.com