Sezgin Saygili

I'm a founding engineer at Patientdesk.ai (YC W26). I build the software that lets AI agents answer calls, book appointments and work with a clinic's existing systems. My recent work focuses on speech recognition and Turkish text-to-speech.

I also built ImpliedOptions, an options analytics app for web and mobile. I studied economics at Aalto University, where I worked as a research assistant.

based	San Francisco / Helsinki
email	[email protected]
cv	Download CV (PDF, two pages)

based

San Francisco / Helsinki

[email protected]

Download CV (PDF, two pages)

What I've built

Patientdesk

I build AI phone agents and the web app clinics use to manage them. The agents answer calls, book and reschedule appointments, check insurance and take payments through integrations with clinic software, including OpenDental, CareStack, CorePractice, Dental4Windows and NexHealth. My work includes call logs and analytics, keeping each clinic's data separate, and letting clinics set up their agents themselves.

TypeScript · Next.js · Python · FastAPI · Supabase · PostgreSQL · GCP · LiveKit · ElevenLabs · Stripe

Duyu & Alania

At Patientdesk AI, Duyu turns Turkish speech into text and Alania turns text into speech. My work covers the streaming APIs, browser demos, API keys and usage limits. Recent changes fixed clicks between audio chunks, released capacity when callers disconnected, and improved how Alania reads numbers, dates, abbreviations and addresses.

Python · FastAPI · PyTorch · WebSockets · TypeScript · Next.js

ImpliedOptions

I built ImpliedOptions for web, iOS and Android: options flow, volatility analysis, strategy modelling and alerts. The web product now includes Theo, an AI research assistant, and 23 tools available through REST and MCP, the protocol used by AI assistants. Users can research trades, manage watchlists and model positions with up to eight option legs. The Python data services ingest trades, identify blocks, sweeps and multi-leg strategies, and store historical data in PostgreSQL.

Python · FastAPI · PostgreSQL · Docker · Next.js · React · Flutter · MCP

VoiceData

I built VoiceData, a platform for paid voice recording and audio review. Contributors apply, submit recordings and receive payouts for approved work. I built the recording, quality checks, review and payout workflows, and used the platform to collect human judgments for the AI Voice Benchmark.

Next.js · Supabase · LiveKit · Python

Open Turkish speech data

I released 1.44 million generated Turkish sentences and a synthetic speech dataset reporting 3,451 hours across 2.05 million clips. The releases include source attribution, quality metadata and known limitations. The speech release also includes a filter list for clips with known pronunciation errors.

Python · PyTorch · vLLM · Hugging Face Datasets · Parquet

News relevancy classifiers

I fine-tuned two BERT models to score news headlines on a four-point relevance scale. FinBERT-ft-v3 uses about 225 hand-labelled Finnish headlines; BERT-ft-v2 uses about 254 English healthcare and AI headlines. Both are published on Hugging Face as small research models, not general-purpose classifiers.

Python · PyTorch · Transformers · Hugging Face

Skills

Languages

Python, TypeScript, SQL

Product

Next.js, React, Flutter

Backend

FastAPI, PostgreSQL, Supabase, Docker, GCP, Vercel

AI & voice

PyTorch, Transformers, TRL, PEFT, vLLM, speech APIs, model evaluation, LiveKit, ElevenLabs, MCP

Data

Pandas, NumPy, econometrics, options analytics

Spoken

Turkish, English, some Finnish