Senior Data Scientist I

**Who we are**

Holmusk is building the largest Real-World Evidence platform, starting with behavioral health. Combining a leading behavioral health database with AI-powered analytics and digital solutions, we are advancing the frontier of evidence generation and fueling innovation.

At Holmusk, we have the privilege of collaborating with internationally renowned psychiatrists/ specialists in behavioral health. We collaborate with established pharmaceutical companies and clinical institutions primarily on behavioral health. We take pride in our diverse workforce and inclusive culture. We believe it takes all kinds of people to build the best products and bring real change to the healthcare space.

**Whom are we looking for**

We are looking for a NLP expert for the Senior Data Scientist-I (NLP) position based in Singapore. The SDS-I will serve as the in-house expert for NLP algorithms applied to healthcare problems and would be responsible for driving the custom NLP projects/ solutions for enrichment of Holmusk’s real world behavioral health database. If this description excites you, come join a diverse and collaborative team of engineers, designers, data scientists, health and business professionals who are passionate about improving healthcare.

If this description excites you, come join a diverse and collaborative team of engineers, designers, data scientists, health and business professionals who are passionate about improving healthcare.

**What is in it for you**
- Opportunity to collaborate with leading SME-s from Mental Health space globally including the US, UK, SG and PRC
- Opportunity to work in a collaborative environment that encourages creativity
- Publish research findings in international peer reviewed journals
- Make major impact on the behavioral health space globally
- Flexible work schedules

**Responsibilities**
- Comprehend requirements for extraction of specific data from unstructured clinician’s notes for the development, training & validation of NLP models
- Conduct literature survey on NLP and decide on appropriate NLP frameworks to meet specific end goals
- Understand the underlying biology/etiology of mental health disorders, care delivery patterns etc. to facilitate annotations for NLP and model development
- Work on developing NLP models in collaboration with junior data scientists which encompasses code review, maintenance of code repositories and code/ model versioning
- Develop strategies for interpreting model insights
- Ensure scientific rigor in model development
- Oversee project development and communicate project updates effectively to managers
- Creation of material including model insights and use cases as required by managers

**Requirements**:

- PhD in Computer Science, Engineering, Statistics, Applied Mathematics, Bioengineering or related fields
- Prior experience in driving NLP based projects
- Have deep knowledge of NLP concepts including but not limited to: Language models like BERT, XLNet, StructBERT etc.; Recurrent Networks, LSTM/ GRU-s, Attention Mechanisms, Transformers, Encoder-Decoder architectures, Siamese Networks; NLP metrics e.g., the BLEU score, Rouge scores, Triplet loss etc.; New models like Reformers, Longformers; Probabilistic NLP algorithms
- Experience in model development and analysis using Scikit-learn, Pandas, Numpy, Tensorflow 2.0 and PyTorch
- Knowledge of relational databases and SQL
- Have familiarity with AWS facilities
- Excellent communication, interpersonal relationship skills and a strong team player

**Other skillsets that will be an added advantage**
- Publications on projects using NLP
- Prior experience in information extraction using language modeling
- Prior experience in ML model deployment / containerization / MLOps on AWS
- Automatic hyperparameter optimization (Keras Tuner/ Hyperopt etc)