We are constantly looking for junior IT developers and analysts with an interest in text mining, Natural Language Processing (NLP) & machine learning.

Please email us your resume to careers@sahanatech.com to be contacted about future openings.
​

Currently, there is one opening as outlined below. This position is ready to be filled now.

Applied Machine Learning Engineer (NLP / AI Systems)

Responsibilities

• Design, develop, and maintain AI/ML solutions to support NIH grant application intake, peer review workflows, and analytics.
• Develop and apply and machine learning techniques (e.g., embeddings, classification, clustering, similarity analysis) on NLP and computer vision for tasks such as reviewer–application matching, keyword extraction, and document analysis.
• Build, evaluate, and iteratively improve machine learning models using structured and unstructured data, including text, documents, and images where applicable.
• Design and implement end-to-end ML pipelines, including data ingestion, preprocessing, feature/embedding generation, model execution, evaluation, and output generation.
• Debug, test, and optimize ML pipelines and tools to ensure reliable, consistent, and reproducible results.
• Refactor and improve code to enhance performance, scalability, and maintainability.
• Work with large and complex datasets, including implementing data validation, quality checks, and preprocessing workflows.
• Conduct experiments to evaluate model performance, analyze results, and refine approaches based on quantitative and qualitative findings.
• Collaborate with cross-functional teams (data scientists, analysts, program staff, and engineers) to translate business needs into practical AI/ML solutions.
• Ensure reproducibility and transparency through documentation, versioning, and structured workflows.
• Communicate methods, results, and limitations clearly to both technical and non-technical stakeholders.
• Stay current with advancements in applied AI/ML, including NLP, embeddings, and generative AI, and evaluate their applicability to NIH use cases.

Required Qualifications

• Strong programming expertise in Python (preferred) and/or R.
• Hands-on experience developing and applying machine learning models and workflows.
• Experience with NLP techniques such as text classification, embeddings, semantic similarity, or related methods.
• Experience with computer vision for medical images.
• Demonstrated ability in innovative ideas in solving complex data problems.
• Experience working with real-world datasets, including data cleaning, preprocessing, and feature engineering.
• Ability to debug, test, and improve complex code and analytical workflows.
• Familiarity with at least one modern ML framework (e.g., PyTorch, TensorFlow, scikit-learn, or equivalent).
• Strong analytical and problem-solving skills, including the ability to evaluate model performance and interpret results.
• Excellent communication skills, with the ability to explain technical concepts to diverse audiences.

Preferred / Desired Qualifications

• Experience with transformer-based models or large language models (LLMs), including practical applications such as text analysis or document processing.
• Experience with reviewer matching, recommendation systems, or document similarity problems.
• Familiarity with distributed data processing tools (e.g., Spark, Dask, Ray).
• Experience with experiment tracking, model versioning, or reproducible workflows (e.g., MLflow or similar tools).
• Familiarity with NIH data systems, biomedical text, or scientific research data.
• Understanding of evaluation metrics (e.g., accuracy, precision/recall) and model robustness.

Education & Experience

• Master’s in data science, Computer Science, Computational Linguistics, or related field (or equivalent experience).
• 3–8+ years of relevant experience in applied machine learning, data science, or a related field.
• Demonstrated experience delivering end-to-end ML solutions, including model development, evaluation, and pipeline implementation.