AI/ML Engineer Intern

Type: Internship (2–3 months, extendable)

Stipend - 5K - 10KLocation: RemoteAvailability - full time / part time

Make My Health is building health products powered by data from wearables and health platforms — Apple Watch, Google Health/Fit, our own custom devices (e.g. the posture wearable), and other third-party health trackers. We're looking for an AI/ML Engineer to turn that raw sensor and health data into meaningful insights and algorithms — things like activity/posture pattern detection, anomaly or risk scoring, personalized recommendations, and predictive health signals — that power features across our app and devices.

What You'll Do

Ingest and normalize health data from multiple sources — Apple HealthKit, Google Health Connect/Fit, custom BLE devices, and manually logged data — into a consistent internal data model.

Design and build ML models/algorithms for health signal detection: e.g. posture/slouch pattern recognition, activity classification, sleep/recovery scoring, anomaly detection, or trend/risk prediction, depending on the product.

Do exploratory data analysis on time-series sensor data (IMU streams, heart rate, steps, sleep stages, etc.) to identify useful features and signals.

Prototype and evaluate models (classical ML and/or deep learning where appropriate) and iterate based on accuracy, latency, and battery/compute constraints for on-device or near-real-time use.

Work with the mobile/firmware teams to figure out what should run on-device (edge inference) vs. in the cloud.

Turn validated models into production-ready pipelines/APIs that the app and devices can call.

Continuously evaluate model performance against real user data and retrain/improve as new devices and data sources are added.

Stay current with relevant health-AI research (wearable sensor fusion, digital biomarkers, etc.) and bring in applicable techniques.

What We're Looking For

Degree (or equivalent experience) in Computer Science, Data Science, Statistics, Biomedical Engineering, or a related field.

Strong Python skills and experience with ML frameworks (e.g. PyTorch, TensorFlow, scikit-learn).

Experience working with time-series or sensor data — wearable/health data experience is a strong plus, but general time-series/IoT/signal-processing experience also counts.

Comfortable with the full ML lifecycle: data cleaning, feature engineering, model training/evaluation, and deployment.

Familiarity with health data APIs/SDKs (Apple HealthKit, Google Health Connect, or similar) is a plus, or willingness to learn them quickly.

Understanding of basic signal-processing techniques (filtering, sensor calibration, feature extraction from accelerometer/gyroscope/heart-rate data).

Ability to work with ambiguous, early-stage product requirements and iterate quickly.

Nice to Have

Experience with edge/on-device ML (TensorFlow Lite, Core ML, or similar) for wearables or mobile apps.

Background in digital health, biomedical signal processing, or clinical data.

Experience building APIs/data pipelines (FastAPI, cloud data pipelines, etc.) to serve models in production.

Familiarity with regulatory/privacy considerations around health data (HIPAA-style handling, data anonymization).

Why This Role

*Work at the intersection of hardware, health, and AI — your models will run on real devices people wear every day.

Shape the algorithms from scratch across multiple health products, not maintain a legacy pipeline.

*Work closely with the founder and product team, with direct visibility from data to shipped feature.