KBKim Boher

Applied AI · ML systems · full-stack product engineering

ML & full-stack
engineer.

Building applied AI and decision systems for high-stakes environments.

10+ years building software and ML systems end to end, combined with experience developing fraud-detection algorithms, analytical tools, and compliance systems inside Israeli government organizations and major financial institutions — including the Israel Securities Authority, where I built algorithms to detect stock-market manipulation.

View projects ↓Experience & credentials
ML / FULL-STACK / APPLIED AI — K-BOHER
Current
Founder & CEO, DeFake
Location
San Francisco, CA
Focus
Applied AI · Product systems
Status
Live in production
ML, AI & Full-Stack Engineering10+ years building and deploying production systemsHarvardX ML & TinyML · full-stack engineering
Government & Financial InstitutionsIsrael Securities Authority · Ministry of Justice · Harel · Ayalon FinanceFraud algorithms · compliance systems · investment control · risk
End-to-End Product DevelopmentFrom technical architecture and model development to productionData · frontend · backend · cloud · blockchain · XR · edge
Patent-Pending Forensic AIFounder & CEO, DeFakeForensic fraud-detection infrastructure across video, images and voice

Capability map

What I build.

Each capability below describes a system I built: the inputs, the technical pipeline, and the production or business result.

01

Applied AI & ML Lifecycle

Building the full ML lifecycle: creating datasets and data infrastructure, training and evaluating models, iterative distillation and compression, MLOps, cloud and on-device deployment, and production monitoring.

View related work →02

Computer Vision, 3D & XR

Built the complete pipeline from dataset creation and mobile video capture through neural-network training and NeRF reconstruction to 3D objects and scenes served in production AR and VR experiences.

View related work →03

AI Product & Full-Stack Engineering

Built production AI products across frontend, backend, data, APIs, and deployment — including a schema-free Chrome extension that understood e-commerce product pages without scraping, analyzed product images, and generated SEO titles, descriptions, keywords, metadata, and upload-ready JSON.

View related work →04

Edge AI & TinyML

Built the complete embedded-ML pipeline from dataset creation and model training through evaluation, distillation, and quantization to deployment on edge devices and live inference on memory-constrained microcontrollers.

View related work →05

Fraud Algorithms & Regulated Systems

Developed the algorithms, analytical tools, and compliance systems used to detect financial and cyber fraud, stock-market manipulation, regulatory breaches, and risk inside Israeli government and financial institutions.

View related work →06

End-to-End Voice AI

Built voice-to-voice systems before realtime voice APIs: STT and TTS models orchestrated around a fine-tuned, self-hosted open-source LLM, with instruction handling, conversational memory, RAG, streaming, buffering, latency control, and speech-interruption handling.

View related work →07

Blockchain & Verifiable Systems

Built production blockchain systems where an AI attester evaluates whether quality requirements are met, creates a verified attestation, activates a Rust smart contract, and automatically transfers payment between smart wallets.

View related work →08

Analytics & Decision Systems

Built customer-acquisition infrastructure for quantitative and qualitative analysis across campaign performance, website behavior, cross-channel journeys, chatbots, leads, and phone calls — helping businesses reduce acquisition cost and increase sales.

View related work →

Project portfolio · production systems

Built before.
Shipped before.

Every preview pairs the technical architecture with a real demonstration or field record. Full case files preserve the implementation details, links, and additional media.

01

Founder & CEO — forensic fraud detection · U.S. patent pending

DeFake — Forensic AI Fraud Detection

A patent-pending six-layer forensic waterfall checks media integrity, origin and provenance, tampering, metadata, hardware fingerprints, watermarks, and neural artifacts across video, images, and voice. It reaches up to 98.9% detection accuracy across 11 AI video generators, then produces the evidence each workflow needs: forensic reports, court evidence, financial-damage evaluations, takedown notices, and verdicts.

Detects AI-generated, tampered, manipulated, and staged content across video, images, and voice — then produces the evidence and next action.

  • Forensic AI across video, images & voice
  • 98.9% across 11 AI generators
  • U.S. patent pending
  • Live product
Visit DeFake ↗Full case file →
Suspect media inDeFake analysisProof, delivered
1Fraudulent insurance claim2Stolen identity video3Fake news footage4Deepfaked court evidence5Synthetic KYC identity
DEFAKE
Media integrityOrigin & provenanceTamper analysis
1Forensic report2Court evidence3Financial damage evaluation4Takedown notice5Verdict
Suspect media in · forensic proof outLIVE on defakes.com
02

Founder — patent-pending human-in-the-loop data system

DeFake Game — Gamifying Forensic Science

A gamified science and data-acquisition system: users analyze uploaded footage or social links, publish checks to a shared feed, vote AI or real, explain their reasoning, and earn credits for correct answers. Behind the interface, those interactions produce structured labels and heatmaps for model evaluation and training — part of DeFake’s patent-pending technology.

Upload footage or paste a social-media link, test whether it is AI-generated, publish the result, and join the community vote.

  • Human-in-the-loop labeling
  • Heatmaps
  • Community consensus
  • Patent-pending technology
Play the DeFake Game ↗Full case file →
DEFAKE / COMMUNITY LABCredits · 240
SOCIAL LINK INGESTEDAnalyzing footage…
YOUR VERDICT
REALAI

Temporal artifacts around face and hands

+20 credits · correct answer
01 · Upload or paste a link02 · Vote AI or real03 · Explain the signal04 · Labels + heatmap created
03

DeFake vertical — damage disputes settled on evidence

Claim Resolution for Car Rental

A mobile-capture and forensic-comparison pipeline guides pickup and return scans, verifies full vehicle coverage, checks every clip for integrity, detects before/after damage, and assembles a claim-ready evidence report.

Scan the car with a mobile phone — damage disputes settle on evidence, not arguments.

  • Built on the DeFake engine
  • 3D capture + forensics
  • Live product
Open live product ↗Full case file →
✓ Front✓ Rear✓ Left side✓ Right side
Renter
Rental service
Start of the tripEnd of the trip
Full-car coverage✓Identity continuity✓Media integrity✓Before / after comparison✓Staged-footage check✓
Damage identified · left front bumper
Verdict — new damage confirmed · claim supported
$500
Renter · pickup

At pickup, the renter scans the car — every side.

04

Founder — computer vision & 3D reconstruction

AR Digital Twin

A complete computer-vision pipeline starts with dataset creation and ordinary mobile footage, trains neural networks for NeRF reconstruction, extracts 3D objects and scenes, and serves them in production AR and VR experiences — roughly 30 minutes of compute instead of weeks of manual modeling.

Plain phone video into a production-ready 3D model in 30 minutes of compute.

  • NVIDIA Inception
  • Microsoft for Startups
  • AWS for Startups
  • NeRF · PyTorch · CUDA
Visit AR Digital Twin ↗Full case file →
See the full neural-network training pipeline & demos →
05

Hardware to model to deployment — solo (HarvardX)

TinyML on Microcontrollers

A complete embedded-ML pipeline built for 256 KB of RAM: dataset creation, model training and evaluation, distillation and INT8 quantization, followed by TensorFlow Lite Micro deployment in C++ and live inference on the microcontroller — no cloud required.

Full-stack ML in 256 KB of RAM — hardware to model to deployment, solo.

  • TensorFlow Lite Micro
  • INT8 quantization
  • Arduino Nano 33 BLE
  • C++ · Mbed OS
Watch training & quantization ↗Full case file →
Kim Boher holding an assembled TinyML rig with Arduino Nano 33 BLE Sense
06

CTO — Telegram mini-app · attested answers · smart-contract payments

Verity — Blockchain Market Research

An end-to-end production blockchain system: a Telegram mini-app collects research answers, a NEAR Shade AI attester evaluates whether quality requirements are met, its verified attestation activates a Rust smart contract, and payment moves automatically into the respondent’s smart wallet.

AI-powered market research for early-stage founders — real users, paid per quality answer.

  • Telegram mini app
  • NEAR Shade agent
  • Rust smart contracts
  • Demo Day
Open live demo ↗Full case file →
07

Realtime voice pipeline · fine-tuned self-hosted open-source LLM

Voice-to-Voice AI Assistant

Built an end-to-end voice-to-voice sales agent before realtime voice APIs existed: speech-to-text and text-to-speech models were orchestrated around a fine-tuned, self-hosted open-source LLM, with instruction handling, conversational memory, RAG retrieval, streaming, buffering, latency control, session state, and speech-interruption handling.

A virtual voice-to-voice sales rep, hand-assembled before realtime voice APIs existed.

  • Fine-tuned self-hosted LLM
  • Conversational memory + RAG
  • STT + TTS orchestration
  • Streaming + interruption handling
Read the build story ↗Full case file →
08

Founder build at Maverick Media — campaign intelligence

Analytical Agent for Customer Acquisition

A customer-acquisition intelligence system combines campaign performance, website behavior, cross-channel user journeys, chatbot leads, and phone calls. It measures both quantity and lead quality, transcribes conversations, extracts sentiment, intent, questions, and objections, and feeds those signals back into campaigns to acquire customers more cheaply and increase sales.

A customer-acquisition management system that combines quantitative and qualitative data to reduce acquisition cost and increase sales.

  • Call transcription + sentiment
  • Source attribution
  • Campaign optimization loop
Full case file →
09

CTO at Kora Media — 80-store e-commerce portal, team of 6 engineers

E-commerce Product Content Generator

A schema-free Chrome extension understands product-page content without external scraping, analyzes the product image with an AI agent, and generates SEO titles, descriptions, keywords, metadata, and upload-ready JSON — without database integration or image storage.

Builds complete SEO product content with an AI agent — from a product page and image to titles, descriptions, keywords, metadata, and upload-ready JSON.

  • Google AI Developer Competition
  • Chrome extension
  • Schema-free
  • Genkit + Node.js
Official entry on ai.google.dev ↗Full case file →
10

Built at the NEAR Foundation’s Oz City incubator

Cryptographic Chain of Custody

An online-camera evidence system verifies footage at capture, creates its cryptographic record, and anchors that record on NEAR — preserving provenance and making later tampering independently detectable.

Documents online-camera footage on-chain and creates cryptographic proof of evidence that can be independently verified later.

  • Blockchain evidence anchoring
  • On-device capture
  • Tamper-proof records
Full case file →
Kim Boher presenting at the NEAR Foundation Oz City incubator
11

Founder — LLM legal agents

Cognitive Intelligence Labs

A multi-agent legal workflow combining document ingestion, evidence analysis, live knowledge bases, legal research, case-building, and client intake around a legal-trained LLM.

An integrated legal suite powered by a legal-trained LLM and specialized agents.

  • Ministry of Innovation Accelerator
  • LLM agent architecture
  • Demo Day
Full case file →
Kim Boher presenting Cognitive Intelligence Labs at the MAOF accelerator demo day
12

Founder, CEO & CTO — software & digital-marketing agency

Maverick Media

Services included fractional CTO leadership, software development, deep-tech and AI development, analytical infrastructure, SEO, marketing automation, and management of Google PPC and social-media marketing campaigns.

Founded a technology agency focused on building companies and their operating infrastructure from the ground up.

  • Fractional CTO
  • Software + AI development
  • Analytics infrastructure
  • Growth operations
Full case file →

Professional trajectory

Domain depth.
Engineering ownership.

Institutional experience across government, financial, and academic environments — combined with 10+ years building software, ML, computer-vision, and AI systems end to end.

  1. 01Hebrew University

    Security operations for a major academic institution

  2. 02Ministry of Justice

    Financial oversight and government casework

  3. 03Israel Securities Authority

    Market-manipulation and financial-fraud detection algorithms

  4. 04Ayalon Finance

    Mutual-fund investment control, fraud detection, and compliance

  5. 05Harel Insurance & Finance

    Real-estate investment control, risk, fraud, compliance, and asset valuation

Kim Boher presenting a technical venture

Finance · government · regulation · fraud detection · engineering · technical entrepreneurship

Degree

M.B.A. — Business Administration, Finance

The Open University of Israel

Degree

B.A. — Philosophy & Economics

The Hebrew University of Jerusalem

2026 · Credential

U.S. patent pending

Multi-layer forensic architecture for AI-content detection, consensus methodology, and evidence preservation. Filed with the USPTO, 2026.

2025 · Credential

Applied ML Engineer — HarvardX

Professional certificate (TinyML 2–4): dataset building, model development and distillation, production deployment, MLOps.

2024 · Credential

Databricks — LLM101x & LLM102x

Large language models: application through production; foundation models from the ground up.

2021 · Credential

Full-Stack Engineer — Ministry of Labor

Professional Software Developer certificate — 98th percentile. Node.js, React, Angular, databases, REST APIs.
Full experience, programs, credentials & technical stack →

Publications & research · 45 articles

The technical thesis
behind the products.

Deepfake forensics, MLOps and AI agents, TinyML and edge AI, voice and multimodal systems — plus a public benchmark whitepaper covering 11 AI video generators. Open any series below to see the additional papers in that field.

Featured research · 2026

Deepfake Detection Benchmark Whitepaper

Public methodology and results across 11 AI video generators.
98.9%Read whitepaper ↗
View all publications by technical field →