We build reliable end-to-end Machine Learning solutions using state of the art technology tools and methodologies

We work with computer vision, natural language processing and predictive analytics developing end to end solutions. Read here what we have been doing recently.
CAF logo
P&G logo
Mining driver safety
Safety is a top priority in mining operations and all precautions must be taken in order to avoid accidents. Distractions while driving can be a big risk, especially when conducting a 24/7 operation. The client therefore wanted to detect and be able to take immediate action if drivers were eating, using the phone or just not following best practices while driving, such as not having both hands on the steering wheel.
We designed and implemented a driver safety application for mining vehicles that operate on NVIDIA Jetson Edge devices using Microsoft’s IoT Hub. We detect when a driver is eating, driving without both hands, etc using computer vision techniques and send the corresponding alerts through an onsite private 4G network.
Technologies leveraged include Python, Tensorflow, Docker, NVIDIA Jetson, React, Azure, Microsoft IoT Hub, Azure DevOps.
Thanks to this innovative solution, the mining operation can be monitored from a dashboard. It helps increase safety by sending early warnings of unsafe behaviors that can be used to give feedback to drivers. Also, it helps reduce the human resources needed to monitor the fleet of trucks that operates on a daily basis providing long term cost reductions.
Matías Deheza
Managing Director, Pi Data Strategy & Consulting
“Marvik is willing, enthusiastic, motivated and communicative, wich is all we could ask for”
Some of our clients
clients logos
Ageing Generative Adversarial Networks
Our client needed to generate images changing a person's age but preserving identity, similar to FakeApp. These applications are very useful when running health prevention campaigns to show visually the effects different lifestyles can have on a person.
younger age
real age
older age
Based on the work of companies like NVIDIA, we implemented an ageing system for human facial photos. It is based on generative adversarial networks utilizing state of the art papers and techniques. Our system receives the photo of a person and alters the person’s age while preserving their unique visual identity. We solved challenges such as developing the production deployment of a scalable solution, optimized for minimum processing time yet while minimizing cloud costs for our client.
Technologies leveraged include Python, Tensorflow, Pytorch, Docker, AWS.
The images generated were very realistic, proving once again the power and potential of deep learning solutions. The MVP achieved good results, providing our client a wide range of possibilities of facial alteration for different applications and purposes.
Managing Director
“They’re very knowledgeable and experienced. Present your vision and let them give their ideas to help you find the best solutions.”
Candidate recommender system
We designed and implemented a candidate recommendation system for a freelance jobs platform. Matching jobs with the ideal candidates is a top priority and the core of its business. Recruiters typically search through dozens or potentially hundreds of profiles in order to find a suitable candidate for a position. Our goal is to reduce the time spent on this manual task, automatically recommending the best profiles for a particular job.
Using natural language processing, we identify the candidates with the most relevant skills for a particular job. State of the art techniques like Google BERT were benchmarked to build the recommender system.
Technologies leveraged include Python, Tensorflow, Docker, Golang, AWS.
Thanks to the implemented recommender system, it is possible to recommend only the suitable candidates for a particular job. It increases the probability of finding a good match between the available open positions and qualified available workers in a timely manner. The solution significantly reduces the time spent by recruiters searching through candidate profiles.
python logo tensor flow logo golang logo aws logo docker logo
Automatic email classification
We worked with a logistics company that receives a large volume of inquiries via email. Queries must first be classified and registered so that our client's agents can process them. Our client's staff spent hours manually sorting these emails. In addition, this task must be carried out in real time in order to comply with the SLAs for handling these orders.
To automate this time-consuming task, we designed and implemented a classification and registration system to hanflr orders and complaints from our client's account executives. Using a natural language processing engine, we were able to interpret the reason for the request and thus be able to classify it automatically.
Technologies leveraged include Python, Tensorflow, Docker, Golang, AWS.
mail classification process
The automatic email classifier system that was deployed helps reduce significantly the human resources needed to perform this task. High confidence results were achieved with the natural language processing engine, resulting in almost all inquiries being correctly classified.
Get in touch with one of our specialists. Let's discover how can we help you.
Training, developing and delivering machine learning models into production
Got a project?
Let’s talk