MS or PhD in Computer Science, Electrical Engineering, Physics, Statistics, or related field, or equivalent experience.
5+ years in data science or machine learning, with 2+ years managing labeled datasets for ML.
Hands-on experience with active learning on real data, including sampling strategies.
Proven ability to identify rare or challenging examples in large datasets.
Experience training deep learning models and using weak supervision for labeling.
Skilled in measuring label quality and correcting errors.
Proficient in Python, SQL, and data pipelines.
Responsibilities
Design and implement active learning strategies for labeling decisions.
Transform model errors and user corrections into new ground truth data.
Identify rare events in datasets for labeling and evaluation.
Manage the ground truth plan, including data selection and prioritization.
Lead a team of annotators, setting priorities and ensuring data quality.
Oversee the development of annotation tools to enhance data collection.
Measure and improve label quality using various metrics and reviews.
Collaborate with data engineers and ML operations to manage label versions and evaluation sets.
Benefits
Health Care Plan (Medical, Dental & Vision)
Retirement Plan (401k, IRA)
Life Insurance (Basic, Voluntary & AD&D)
Paid Time Off (Vacation, Sick & Public Holidays)
Family Leave (Maternity, Paternity)
Short Term & Long Term Disability
Work From Home
Free Food & Snacks
Wellness Resources
Stock Option Plan
Full Job Description
Senior Machine Learning Engineer - Active Learning The role
This Senior Machine Learning Engineer will own the loop from data to labels to improved models. You will use active learning and weak supervision methods to generate labels, decide what to label next, and turn errors we find in the field into new labels.
This is a hands-on role. You will be expected to write code, train models, analyze data, and document experiments. You will work with data scientists, annotators, product, and engineers to get labels and improve models. You will direct the development of annotation tools and the work of our annotators to speed up and scale labeling.
Success in this role is measured by the reduction in cost per annotation (i.e., time per annotation), while keeping label quality at or above our targets.
Responsibilities:
Design and run active learning to choose which homes, devices, and time periods to label next, based on where models are uncertain or wrong.
Turn bad detections, field accuracy results, and user corrections into new ground truth, and track whether retrained models improve.
Find rare events and hard cases in home data, such as uncommon or mislabeled devices, and add them to labeling and evaluation sets.
Own the ground truth plan: which data, how much, and in what order.
Direct a team of annotators: set priorities, track throughput, and provide guidance. Set data quality standards.
Direct development of our annotation tool. Add features that enhance our ability to collect new and better data, including features that rely on models.
Measure and improve label quality through metrics, outlier detection, human review, etc.
Work with data engineers and ML operations to version labels and track which labels trained which model. Keep evaluation sets separate from training data so offline results predict performance in the field.
Be a good teammate: review code, provide peer feedback on research and experiments, and contribute to shared documentation. Help mentor/coach less experienced team members.
Requirements
Qualifications:
MS or PhD in Computer Science, Electrical Engineering, Physics, Statistics, or a related field, or equivalent experience.
5+ years of experience in data science or machine learning, including 2+ years building or managing labeled datasets for ML.
Hands-on experience applying active learning to real data, including choosing a sampling strategy and measuring whether it helped.
Experience finding rare or hard examples in large datasets, i.e., from model errors, uncertainty, or similarity search.
Experience training deep learning models, and with weak supervision or model-assisted labeling.
Experience measuring label quality and fixing label errors.
Experience with Python, SQL, and data pipelines.
A track record of working with other teams, i.e., product, software, or hardware.
Preferred qualifications:
Experience with time series, audio, sensor, or other signal data.
Experience leading an annotation team or directing development of annotation tools.
Experience using embeddings from large or foundation models for data analysis.
Logistics:
Location: able to work from our Cambridge, MA office at least 2 days per week.
Salary range: $165,000 to $185,000
Work authorization: required.
Benefits
Health Care Plan (Medical, Dental & Vision)
Retirement Plan (401k, IRA)
Life Insurance (Basic, Voluntary & AD&D)
Paid Time Off (Vacation, Sick & Public Holidays)
Family Leave (Maternity, Paternity)
Short Term & Long Term Disability
Work From Home
Free Food & Snacks
Wellness Resources
Stock Option Plan
About Sense
Sense is a technology company that develops and manufactures LiDAR and 3D sensing solutions for autonomous vehicles, industrial automation, and other applications. The company's products are based on its proprietary flash LiDAR technology, which enables high-resolution 3D imaging at long ranges and high speeds. Sense's solutions are designed to be compact, low-cost, and highly reliable, making them suitable for a wide range of applications. The company was founded in 2016 and is headquartered in Sunnyvale, California.
