Senior Applied ML Algorithm Engineer

WHOOP

Boston, MA

On-site

Who this role is best for

Best suited to candidates with experience in embedded systems and physiological signal processing working in wearable technology.

Best fit for

Candidates with 5+ years of experience in embedded systems and sensor data processing
— “5+ years of experience developing signal processing and machine learning algorithms for time-series or sensor data in real-world applications.”
Individuals with a strong background in translating research into production-ready models
— “Collaborate with Data Science, Software, Product, and domain experts to translate research findings into production-ready capabilities.”
Candidates who can optimize models for power, memory, and latency constraints
— “Demonstrated experience deploying machine learning models to resource-constrained embedded systems, including optimization across accuracy, power, memory, compute, and latency.”

Things to consider

Relocation to Boston, MA is required if not already based there
— “The successful candidate must be prepared to relocate if necessary to work out of the Boston, MA office.”
Experience with physiological signals or wearable sensors is preferred
— “Experience with physiological signals or wearable sensors is a plus.”

How to stand out

Highlight projects involving real-time sensor data processing and embedded deployment
— “develop and deploy signal processing algorithms and machine learning models that transform raw sensor data into accurate, reliable, and real-time physiological insights on WHOOP devices.”
Showcase ability to optimize models for power, memory, and latency
— “optimizing signal processing pipelines and on-device inference for accuracy, power, memory, compute, and latency.”
Emphasize collaboration with firmware and hardware teams on algorithm integration
— “Partner closely with Firmware and Hardware teams to integrate algorithms into production firmware.”
Demonstrate experience with defining rigorous validation plans for models
— “Define performance metrics and rigorous validation plans, combining offline evaluation, lab-based experiments, real-world data analysis, and on-device testing.”
Show your ability to independently investigate algorithmic problems and validate results
— “Ability to independently investigate complex algorithmic problems, design rigorous validation experiments, and communicate technical tradeoffs.”

Pace · Fast PacedCollaboration · HighAutonomy · HighDecision Impact · Team

Derived from job-description analysis by Serendipath's career intelligence engine.

What success looks like

Algorithm development
Model training
Production validation

Typical background

Machine LearningSignal Processing

Skills & requirements

Required

Signal ProcessingMachine LearningC/c++ ImplementationFirmware Integration

Preferred

Physiological SignalsWearable Sensors

Stack & domain

Signal ProcessingFeature ExtractionMachine LearningC/c++TensorFlowPyTorchscikit-learnProblem SolvingCollaborationCommunicationWearable TechnologyPhysiological DataRecoveryTrainingSleep

About the role

Original posting from WHOOP via Ashby

At WHOOP, we're on a mission to unlock and inspire performance for life. WHOOP empowers members to perform at a higher level through a deeper understanding of their bodies and daily lives. Our wearable technology collects rich physiological data, providing members with actionable insights into their recovery, training, and sleep.
We are seeking a Senior Applied ML Algorithm Engineer to develop and deploy signal processing algorithms and machine learning models that transform raw sensor data into accurate, reliable, and real-time physiological insights on WHOOP devices. In this hands-on role, you will own algorithm development from data analysis, model training, and Python prototyping through efficient C/C++ implementation, firmware integration, and production validation. Working closely with Data Science, Firmware, Hardware, and domain experts, you will deliver robust on-device algorithms that improve the member experience while meeting the power, memory, compute, and latency constraints of wearable hardware.
RESPONSIBILITIES:
Design and develop algorithms that combine signal processing, feature extraction, and machine learning to derive meaningful physiological insights from wearable sensor data.
Analyze large-scale, noisy sensor datasets to train and evaluate models, identify performance gaps, and improve accuracy, robustness, and generalization across diverse members and real-world conditions.
Translate algorithm prototypes and trained models into production-ready C/C++ implementations, optimizing signal processing pipelines and on-device inference for accuracy, power, memory, compute, and latency.
Partner closely with Firmware and Hardware teams to integrate algorithms into production firmware, validate execution on target hardware, and resolve differences between prototype and embedded performance.
Define performance metrics and rigorous validation plans, combining offline evaluation, lab-based experiments, real-world data analysis, and on-device testing to assess algorithm accuracy, reliability, and efficiency.
Collaborate with Data Science, Software, Product, and domain experts to translate research findings into production-ready capabilities, investigate post-deployment performance gaps, and drive continuous algorithm improvement.
QUALIFICATIONS:
5+ years of experience developing signal processing and machine learning algorithms for time-series or sensor data in real-world applications.
MS or PhD in Electrical Engineering, Biomedical Engineering, Computer Science, or a related quantitative field, or equivalent practical experience.
Strong foundation in digital and statistical signal processing for noisy time-series data. Experience with physiological signals or wearable sensors is a plus.
Proficiency in Python for data analysis, model development, and experimentation, and C/C++ for implementing efficient algorithms in embedded firmware.
Experience developing, training, and evaluating machine learning models using frameworks such as TensorFlow, PyTorch, or scikit-learn.
Demonstrated experience deploying machine learning models to resource-constrained embedded systems, including optimization across accuracy, power, memory, compute, and latency.
Ability to independently investigate complex algorithmic problems, design rigorous validation experiments, and communicate technical tradeoffs with firmware, hardware, and data science partners.
Strong commitment to embracing and leveraging AI tools in day-to-day tasks, ensuring AI-assisted work aligns with the same high-quality standards as personal contributions.
This role is based in the WHOOP office located in Boston, MA. The successful candidate must be prepared to relocate if necessary to work out of the Boston, MA office.
Interested in the role, but don’t meet every qualification? We encourage you to still apply! At WHOOP, we believe there is much more to a candidate than what is written on paper, and we value character as much as experience. As we continue to build a diverse and inclusive environment, we encourage anyone who is interested in this role to apply.
WHOOP is an Equal Opportunity Employer and participates in E-Verify to determine employment eligibility. It is unlawful in Massachusetts to require or administer a lie detector test as a condition of employment or continued employment. An employer who violates this law shall be subject to criminal penalties and civil liability.

Source: WHOOP careers (Ashby)