Embedded Engineer in Honeycomb Software

Honeycomb Software is an innovative fast growing software company that develops digital products for startups and online businesses.

We are looking for a passionate and talented embedded engineer who will be responsible for machine learning inference on edge devices like Nvidia Jetson or tensor chips. He will collaborate with other scientists and engineers to optimize the deployment of Machine Learning, and optimization models on edge devices. He/she will be responsible for minifying the model/data pipeline so it can run on such a low-power device. Besides innovation, you will work closely with seasoned scientists, engineers, and program managers to deliver your optimized inference pipeline into real products. Your work will directly impact our customers in different industries. You are the ideal candidate if you are enthusiastic about delivering products and solutions that are robust and dominant in the market. You thrive in ambiguous environments that require finding the best answers to open problems that have not been solved before. You leverage your exceptional technical expertise in fast-paced research and development and apply your fundamental understanding of computer science, mathematics, and statistics to create reliable, scalable high-performance products. Your strong communication skills enable you to work effectively with both business and technical partners. You have hands-on experience making the right decisions about technical methods. You strive for simplicity and elegance and demonstrate significant creativity and sound judgment backed by real data. Most of all, you are willing to take calculated risks, learn by trying, and grow as a team.

REQUIREMENTS:

• MS/PhD degree in Computer Science, Electrical Engineering, Machine Learning, or a related field
• Experience deploying deep learning models on edge devices like Nvidia Jetson
• Deep knowledge of C/C++
• Python/TensorFlow is a big plus
• Excellent written and verbal communication skills in English

RESPONSIBILITIES:

• Optimize ML and Deep Learning models to run on Edge devices line Jetson Nvidia with minimal CPU/GPU and memory consumption
• Pruning deep learning model to use fewer resources
• Optimize data pipeline to work with limited computation/energy resources
• Work with PMs to define use cases, collect data, and benchmark the result

WE OFFER:

• Friendly working atmosphere
• Interesting long-term projects and challenging tasks with a team of professionals
• Opportunities to study, develop and improve your skills
• Flexible work schedule
• Paid vacations, sick leaves and social benefits from the company
• Competitive salary and regular performance reviews
• Project exposure and ownership that impacts our users, product, and business
• Challenging technical tasks, fast learning cycles, and meaningful feedback
• Project exposure and ownership that impacts our users, product, and business

If you are interested in this position, please send us your CV! Let’s talk!