Senior Computer Vision Engineer

Job Description

Job Description

Please note this is a hybrid role expected in office (SF) on Tues and Thurs.

Glacier is a Series A startup based in San Francisco that builds robots and image data collection devices to improve recycling facilities in the following ways :

a robot that identifies and sorts materials inside recycling facilities

an analytics system that tracks recyclables and reports metrics to key stakeholders in the industry.

These technologies are already helping to divert tons of recyclables (literally!) from landfills every day.

We’re looking for a talented machine learning engineer to help us further improve these game-changing technologies.

About us :

We’re a small team based in SF and as an early ML team member you’ll have a significant role in shaping Glacier’s future.

Our founders come from Facebook engineering and Bain consulting.

We’re backed by top-tier VCs with extensive technical and industry expertise.

We have a fleet in production and a robust pipeline of upcoming deployments.

About the role :

You will own the full ML model lifecycle—from data ingestion to production deployment and monitoring—across cloud, local, and on-prem infrastructure. You will be responsible for training computer vision models, building infrastructure for large-scale inference and data analysis, and driving new projects to use machine learning to reduce waste.

Your responsibilities :

Drive the performance of our computer vision models. That includes : building ML infrastructure, fine tuning our model and training process, improving our data collection, and ensuring high quality, diverse training data.

Develop, train, evaluate, and deploy ML models that directly support customer-facing products.

Maintain a high bar for model performance monitoring, alerting, and retraining pipelines to ensure measurable business impact.

Build automation and experimentation into our full ML lifecycle, enabling us to deploy systems and create impact at scale.

Collaborate cross-functionally with machine learning engineers, software engineers, hardware engineers, product / program managers, and the sales team to solve real customer problems.

Partner with our Head of ML on long-term ML strategy, and help define and scope high-impact R&D initiatives.

Help shape the long-term product roadmap — we’ve got big ideas for the future of waste-ending technology, and we’re excited to bring in yours too.

Requirements : (If you don't think you meet all of the criteria but are excited about us, please reach out anyway!)

4+ years experience developing machine learning models in a deep learning framework like Tensorflow / Keras or Pytorch.

2+ years of experience in Computer vision model development with object detectors - mandatory

Experience with building machine learning infrastructure (training pipelines, hyperparameter tuning, experiment tracking, etc).

Strong expertise in Python and hands-on experience in SQL databases.

Experience with Linux environments for development and deployment

Proficiency with the SciPy ecosystem (numpy, pandas, matplotlib) and distributed computing in frameworks such as Ray.

Experience deploying ML models in production and monitoring their performance over time.

Demonstrated ability to translate ML work into business impact.

Ability to work from our San Francisco office (SOMA neighborhood) twice a week.

Why Join Us?

Mission-Driven Work – Be part of a company dedicated to sustainability and ending waste.

Cross-Functional Impact – Work cross-functionally with an expert, mission-driven team where your technical decisions shape both the product and the company.

Backed to Succeed – Our founders bring experience from Facebook and Bain, and we’re supported by top-tier investors with deep technical and industry expertise.

The total cash compensation range for this role is $150,000 - $200,000. In addition to cash compensation, Glacier also offers competitive equity compensation and benefits. The final compensation for this role will depend on many individualized factors, including job-related skills and knowledge, experience level, interview performance, and other factors.