Dmytro F. Profile

EXPLORE

5.0

(2 reviews)

You're now following

Error following user.

This user does not allow users to follow them.

You are already following this user.

Your membership plan only allows 0 follows. Upgrade here.

Successfully unfollowed

Error unfollowing user.

You have successfully recommended

Error recommending user.

Something went wrong. Please refresh the page and try again.

Email successfully verified.

$75 USD / hour

san francisco,

united states

$75 USD / hour

It's currently 9:23 AM here

Joined April 10, 2017

0 Recommendations

Dmytro F.

@DmytroF

5.0

(2 reviews)

2.3

100%

$75 USD / hour

san francisco,

united states

$75 USD / hour

100%

Jobs Completed

100%

On Budget

100%

On Time

N/A

Repeat Hire Rate

Full-stack with machine learning experience / PM

Hi all, I'm in San Francisco, CA. Worked on multiple automation, AI/ML projects (CV, NLP, Analytics) before, with roles ranging from engineering, data ops. to Head of AI. Have a deep project delivery experience (was a founder in a couple of companies), but also not shy to work on existing code-base, no matter if it's in a good shape or not. Available to work remotely from SF, open to relocation and business trips/meetings with customers around the world. My skills: [login to view URL] My LinkedIn: [login to view URL] My certifications related to AI/ML stack: ML engineering: [login to view URL] SDC engineering: [login to view URL] Thanks, looking forward to talking with you.

See all Python Developers in United States

Contact Dmytro F. about your job

Portfolio

The system automatically detects threat levels originating from hundreds of video streams (CCTV cameras, dashcam/drone footage, etc). The algorithm weighs threat levels according to object & scene classification, quantity, velocity, and other factors. The user interface automatically alerts the human operators and zooms into streams requiring immediate attention. The system increases situational awareness, reduces reaction time, reduces human labor and hardware requirements in both real-time surveillance and historical footage analysis.
Our system enables better Situational Awareness. This is achieved through (1) artificial experts who monitor multiple live video feeds in real-time and (2) automatic triage system ranking and weighing all incoming signals. This allows one human operator to handle hundreds of live imaging feeds, reducing the cognitive burden and improving reaction time.

Computer Vision / AI triage system

An extendable, scalable and distributed streaming platform built on top of Apache Kafka enables the integration of multiple data sources with core monitoring elements. Each data source submits data into a separate communication channel based on the media type, multiple media monitoring agents processes data and extracts signals from raw data based on a set of predefined rules and advanced machine learning models.

Capabilities: Advertising monitoring; Uptime and quality monitoring; Content logging; Sentiment analysis; Targeted monitoring/image search

Media Monitoring: extendable monitoring hub + AI agents

Computer Vision / AI triage system

Media Monitoring: extendable monitoring hub + AI agents

Reviews

Changes saved

Showing 1 - 2 out of 2 reviews

Filter reviews by:

5.0

$70.00 USD

Deploy and serve my tensorflow estimator on Google Cloud

Well skilled developer. Knows his way around stuff. Completed project perfectly on time and budget. I highly recommend him.

Python

Google App Engine

Machine Learning (ML)

Syed Shaheryar Hussain S.

@sshussain270

•

6 years ago

5.0

$25.00 USD

I need about 200 email submissions from different machines/proxy

Dmytro is one of the greatest freelancers i've ever worked with. Magic touch, super friendly, great communications. Excellent experience ! Thank you!

Programming

Ito Z.

@zoola

•

6 years ago

Qualifications

Udacity

2016

https://confirm.udacity.com/5CWGMKJP - focused on Keras and Deep Learning

Udacity

2018

https://confirm.udacity.com/LGKZNADD - Deep Learning, Computer vision, robotics and AI/ML.

Publications

Unified vector space mapping for knowledge representation systems

Arxiv - Cornell University Library

The problem of direct Human - Knowledge Representation System interface is addressed and a concept of adaptive decoder proposed for the purpose of interaction with previously described unified mapping model. In combination these two approaches are suggested as basis for a development of a new generation of knowledge representation systems.

Evolutionary algorithm based adaptive navigation in information retrieval interfaces

Arxiv - Cornell University Library

Browsing search approach, the ability of the algorithm to adapt navigation to users interests, collaborative refinement and the self-organising features of the system are the main factors making such architecture effective in various fields where non-structured knowledge shall be represented to the users.