Hausa NLP Data Scientist

Responsibilities

• Benchmark candidate listening platforms on how much relevant Hausa content they capture.
• Fine-tune African-language models AfroXLMR or AfriBERTa class on project-coded Hausa data.
• Automate a coding category only once the model reaches a macro-F1 score of 0.80 or higher against human coding.
• Monitor model accuracy monthly and retrain models when performance drifts.
• Run time-series analysis and comparisons across the study phases.
• Maintain the secure, encrypted data warehouse and the project code repository.

Required experience

• MSc or higher in Computer Science, Natural Language Processing, Data Science, Statistics or Computational Linguistics.
• At least 3 years of professional experience in applied NLP or machine learning.
• Hands-on experience fine-tuning transformer models.
• Experience with African or other low-resource languages, ideally Hausa.
• Strong Python skills Hugging Face, pandas, scikit-learn and working knowledge of SQL.
• Native Hausa speaker with fluent English.

Preferred experience:

• Publications or open-source work on Hausa NLP for example AfriSenti or NaijaSenti.
• Topic modelling BERTopic and time-series analysis in R or Python.

Skills and attributes:

• Rigour in measuring and reporting model accuracy honestly.
• Able to explain technical limits to non-technical colleagues.

Method of Application

Interested and qualified candidates should send their applications in one PDF to: info@aid-health.org using “SL Application – [Job ID] – [Full Name]” as the subject of the mail.

Candidates should send one PDF containing:

• A CV (maximum 4 pages);
• A one-page cover note;
• One work sample;
• Two referees.

Note

• Engagement depends on the contract being awarded.
• AIDHealth never charges a fee at any stage of recruitment.
• Women and persons with disabilities are encouraged to apply.