[Hiring] Data Scientist @Lyra Health

Role Description

We are searching for an experienced data scientist to be a technical partner in translating our deep domain expertise into statistically robust predictive models.

• Remote: The role is fully remote to be based in South Africa.
• Hours: 8am to 5pm. The role is a permanent five (5) day a week role (Monday to Friday).
• Flexibility: Given the global nature of the business, the successful candidate will be expected to demonstrate flexibility in their working hours and will be required to come into the office once a month (if Johannesburg based).

Key Responsibilities

• Predictive modelling (machine learning) - hands-on experience building, validating and interpreting predictive models in Python.
• Time-series analysis and forecasting - experience with models that analyse data over time to make a future prediction.
• Applied statistical analysis - ability to test for the statistical significance of a trend.
• Creative feature engineering - must be able to use thousands of individual data points into a handful of organisational level predictors.

Skills and Experience

• Advanced SQL - strong expertise in SQL, comfort with writing complex queries.
• Collaborative ability to turn a hypothesis into a model - must have excellent listening and communication skills and be able to translate an intuitive hypothesis into a model.
• Proven experience handling sensitive data - must understand the ethical implications of predictive modelling in mental health.

Requirements

• Advanced SQL & Data Architecture:
  • Mastery of SQL with the ability to adapt queries across dialects (e.g., T-SQL to Snowflake).
  • Experience navigating complex relational databases to extract multi-modal datasets.
• End-to-End Python Modelling: Hands-on experience using the Python data stack (Pandas, NumPy, Scikit-Learn) to build, validate, and deploy predictive models.
• Forecasting & Time-Series Analysis: Expertise in analysing longitudinal data (data over time) using libraries like Prophet or Statsmodels to create forward-looking risk forecasts.
• Creative Feature Engineering: A proven ability to transform messy, individual-level behavioural and clinical data into meaningful, aggregated organizational-level metrics.
• Applied Statistics: Strong foundation in statistical significance testing, ensuring that discovered trends are mathematically sound and not just random noise.
• Collaborative "Translator" Skills: Ability to bridge the gap between deep domain intuition and technical execution. Must be able to explain complex model outputs to senior leadership and collaborate with Data Engineering to ensure model stability during warehouse migrations.
• Data Ethics & Privacy: Experience working with sensitive clinical or wellbeing data, with a strict adherence to privacy standards (GDPR/POPIA/HIPAA) and anonymisation protocols.

Benefits

• In accordance with the Employment Equity Act, preference will be given to suitably qualified candidates from designated groups, including persons with disabilities.
• We are an Equal Opportunity Employer. We do not discriminate on the basis of race, color, religion, sex (including pregnancy), national origin, age, disability, genetic information or any other category protected by law.