Machine Learning Engineer, Perception

About Treeswift:

Treeswift is revolutionizing decision-making for critical energy infrastructure in the face of rising threats like severe storms and wildfires.

After cutting our teeth developing AI models for forests in the timber sector, we are growing rapidly in the utility sector. In the U.S. alone, hundreds of thousands of miles of transmission lines and millions of miles of distribution lines need to be monitored and managed to reduce hazards, such as encroaching vegetation, that can cause outages or fires. With the rapid growth of renewable energy this infrastructure footprint is expected to more than double in the coming years creating more assets to defend than ever before.

Treeswift’s mission is to deliver effective scalable technology to manage large-scale distributed infrastructure, starting with managing the risks posed by vegetation surrounding these assets. We do so by innovating across the technical stack. LiDAR and imagery data is collected by our sensor packs mounted on backpacks and vehicles to seamlessly integrate into customer operations. We then leverage AI (i.e. computer vision, etc…) to transform this data into actionable insights delivered to decision-makers in our software platform. 

We are early in our journey and focused on finding ground truth by working closely with our customers and using this understanding to deliver real value to our customers. To tackle this challenge we have brought together mission-driven robotics experts from top academic institutions (Penn, Caltech, etc…) and professionals with deep industry experience (Palantir) in enterprise software development. We hope you’ll join us.  

About the Role:

Treeswift is seeking a highly skilled and motivated Machine Learning Engineer to join our team. You will play a pivotal role in developing and deploying state-of-the-art computer vision solutions to advance our mission. We are looking for an exceptional candidate with a proven track record of training and deploying computer vision models at scale. If you are a passionate and experienced engineer eager to contribute to the future of land monitoring and management we encourage you to apply. 

This is a full-time, hybrid/2-day a week in person role, with a strong preference for candidates based out of our NYC or Philadelphia office. 

Key Responsibilities 

• Develop machine learning models that revolutionize our customers’ businesses. Treeswift develops machine learning algorithms that upend the cost and accuracy of vegetation management for energy infrastructure. In this role you will be responsible for bringing innovative ideas and rapid execution to new and existing models. In the course of development, you will collaborate closely with other teams (product, operations etc…) and have an opportunity to interact with end-users. Our machine learning model development focuses on two primary areas: (a) LiDAR point cloud models to classify and segment landscapes and infrastructure and (b) image models to derive vegetation attributes such as species and health. 

• Create a best-in-class feedback loop to accelerate model development. You will improve Treeswift’s ability to assess model performance and adapt to new operating conditions at scale. Treeswift’s cutting edge model development involves significant investment in a proprietary dataset to train our models.

• Help Treeswift scale. In this role you will be expected to bring prior experience with commercial machine learning model development and deployment to help Treeswift cost-effectively scale its technology to serve a growing number of customers and use cases. You will be responsible for enabling effective collaboration on model development within the engineering team, and you will contribute to efforts to ensure reliable and robust performance of models in production.

Required Skills 

• Proven track record of training and deploying machine learning models at scale for commercial use cases. 

• Experience in semantic segmentation and object detection using point cloud data.

• Experience creating, curating, and cleaning training datasets

• Strong programming skills in Python 

• Expertise in deep learning libraries such as PyTorch, TensorFlow, or similar.

• Excellent problem-solving and analytical abilities.

• Exceptional communication and collaboration skills.

Preferred Skills

• Expertise in instance segmentation demonstrated through relevant projects.

• Experience with one or more of: Sensor Fusion, SLAM, Visual Odometry.

• Experience with image processing techniques and computer vision fundamentals.

• Building and using cloud-based training and inference pipelines.

• 5+ years of professional experience or 3+ years with an advanced degree. 

• Experience with deep learning training frameworks such as MLflow, Lightning, Weights and Biases, or similar.

What We Value

• Mission first. We value low ego team members who focus on working towards the best outcomes for the customer and the business, regardless of who gets the credit. 

• Truth seeking. We don’t always have perfect information to make decisions, but we seek to constantly get closer to the ground truth and aren’t afraid to learn we were wrong in the process.

• Owners mindset. If you see an opportunity for improvement, run with it. We believe that good ideas can come from anywhere, no matter your role.

Benefits

• Comprehensive medical, dental and vision insurance 

• Life insurance package and disability coverage 

• Stock options

• Paid leave for new parents 

• Unlimited PTO

• 401K

Salary

The estimated salary range for this position is $160,000-$180,000. Total compensation for this position is determined by skills, qualifications, relevant work experience, location, and other factors. This salary estimate excludes the value of any potential bonuses; the value of any benefits offered; and the potential future value of any long-term incentives. This information is provided per the New York City Human Rights Law. Please note that the range provided is applicable only to New York City-based applicants. Base compensation may vary if the work location is outside of New York City.

Treeswift  is proud to be an equal opportunity employer. We provide employment opportunities without regard to age, race, color, ancestry, national origin, religion, disability, sex, gender identity or expression, sexual orientation, veteran status, or any other protected status in accordance with applicable law.

If you require any accommodations during the recruitment process, whether it be alternate forms of material, accessible meeting rooms, etc., please let us know and we will work with you to meet your needs.