Backend Developer + ML Engineer

Role Overview:
We’re looking for a
Backend + ML Engineer
who can build scalable APIs, manage secure patient data flow, and support AI model integration. You will work alongside AI engineers, front end developers, and field researchers to operationalize models for real-time use, especially on edge devices.
Responsibilities:
Design and develop robust backend systems to handle real-time patient data and ML outputs.Integrate machine learning models (e.g. symptom-to-diagnosis classifiers, RCA engines) with APIs and the main O-Health app.Optimize model serving pipelines (e.g. using TorchServe, FastAPI, or ONNX).Manage data pipelines for de-identified OPD datasets used in model training and inference.Implement data encryption, anonymization, and consent-based data access.Set up backend support for multilingual voice and text processing.Support versioning and A/B testing of health algorithms.
Required Skills:
Backend Engineering
Strong in
Python
with frameworks like
FastAPI ,
Flask , or
Django .Experience with
RESTful APIs , WebSockets, and asynchronous data flows.Familiar with
PostgreSQL ,
MongoDB , or time-series databases.Working knowledge of
Docker ,
Git , and
CI/CD pipelines .
Machine Learning Ops
Hands-on with
PyTorch ,
Scikit-learn , or
TensorFlow
for inference integration.Comfortable with
model optimization ,
quantization , and
edge deployment
formats (e.g. ONNX, TFLite).Familiarity with
language models (LLMs)
and
multilingual NLP
is a strong plus.Knowledge of
data preprocessing ,
tokenization , and
feature engineering
for clinical/NLP tasks.
Other Preferred Skills
Understanding of
HIPAA/GDPR compliance .Experience working on
healthcare ,
social impact , or
AI-for-good
projects.
What You'll Impact:
You’ll play a pivotal role in connecting machine learning research with field-ready healthcare tools. Your work will help scale diagnosis support systems to thousands of underserved patients and power multilingual health consultations in real-time.