What I'm Working On

Projects I've built.

SaaS

Go Interview

In progress

Go Interview is Gong for job seekers: research, record, review, and sharpen every interview so you stop guessing and start closing the right offer.

Most job seekers treat interviews like a test they need to pass. Go Interview treats your job search like what it really is: a sales cycle. Research companies and prepare with intention before you walk in. Record and review your interviews with AI that gives you honest, actionable feedback. Track every company from application to offer. Surface the patterns in how you present, where you stumble, and which roles genuinely align with your skills. Get sharper with every conversation and focus your energy on the opportunities worth winning.

Go Interview - land the offer you actually wantGo Interview - land the offer you actually want gointerview.app Visit gointerview.app

An LLM-powered system that transcribes, scores, and reviews interview recordings to generate structured, actionable feedback across every round of a job search.

Each interview is scored across configurable dimensions tailored to the round type (recruiter screen, hiring manager, technical deep dive, exec final), with talk-time ratio analysis, sentiment trajectory tracking, and automatic question extraction that builds a searchable bank across all interviews. Transcription runs a dual-path pipeline with NVIDIA Parakeet TDT and NeMo Sortformer on a GCP spot T4 for GPU-accelerated diarized transcription with word-level timestamps. Reviews route through Claude API or locally-hosted Scout, turning every recorded conversation into structured, actionable feedback, identifying exactly where momentum built, where it dipped, and what to adjust for the next round.

PythonGCPNeMoLLMGPU InferenceDiarizationSpeech-to-Text
Screenshots
Overall Analysis - cross-company metrics and AI-generated assessment across all interviews
Overall Analysis - cross-company metrics and AI-generated assessment across all interviews
Process Insights - advance/develop/pass recommendation with dimension scores and coaching
Process Insights - advance/develop/pass recommendation with dimension scores and coaching
Review Assessment - AI-generated performance analysis with PDF and transcript exports
Review Assessment - AI-generated performance analysis with PDF and transcript exports
Sentiment Trajectory - energy tracking over time with labeled momentum phases
Sentiment Trajectory - energy tracking over time with labeled momentum phases
Transcript Playback - diarized audio with speaker labels, timestamps, and key moments
Transcript Playback - diarized audio with speaker labels, timestamps, and key moments
Follow-up Email - AI-drafted thank-you email tailored to interview content
Follow-up Email - AI-drafted thank-you email tailored to interview content
Example Reports

First page of each report.

Overall Interview Analytics Page 1
Overall Interview Analytics
Call Review Page 1
Call Review
Account Intelligence Brief Page 1
Account Intelligence Brief
$$$

Prediction Market Arbitrage Platform

In progress

A fully automated arbitrage engine that captures pricing discrepancies between Polymarket and Kalshi prediction markets.

Built in Rust for low-latency execution across a dual-VPS architecture with an Amsterdam node running the core arb engine and a NYC node acting as a lightweight gRPC executor proxy for minimal round-trip to Kalshi's servers. Infrastructure provisioned with Pulumi, nodes connected via WireGuard, and a Telegram bot for remote monitoring and control. Targeting ~5% monthly returns on deployed capital.

RustgRPCPrediction MarketsLow-LatencyReal-Time StreamingTelegram Bot
Screenshots
Dashboard - live signals, trades, capital allocation, and market pairs with real-time spread tracking
Dashboard - live signals, trades, capital allocation, and market pairs with real-time spread tracking
Execution stats, capital efficiency, and cost of ownership breakdown
Execution stats, capital efficiency, and cost of ownership breakdown
Telegram Bot - real-time alerts, trade commands, and engine control via mobile
Telegram Bot - real-time alerts, trade commands, and engine control via mobile
To Do
  • Expanding into market making, quoting both sides of the book to capture spread as a standalone profit source beyond cross-platform arbitrage.
MCP

Write Like Me

On hold

A model-agnostic system that captures and reproduces your personal writing voice across any LLM.

Ingests a tagged corpus organized by register, distills it into a structured style guide, and uses embedding-based few-shot retrieval at generation time to match tone and voice. Supabase backs the corpus store and vector search, handling document metadata, register tags, and embedding lookups in one layer. Exposed as an MCP server so any compatible client can call your voice as a tool. Building toward a custom fine-tuned model using PyTorch and QLoRA, quantizing an open-source base model to 4-bit precision and training a lightweight low-rank adapter on the corpus to internalize style patterns directly in model weights, producing a small, swappable adapter rather than a full retrained model.

PythonPyTorchMCPRAGSupabase
To Do
  • On hold while focusing on Go Interview.