Machine Learning Engineer
Allozymes is a deep tech company based in Singapore. We are revolutionising the way industry uses enzymes for manufacturing chemicals and natural compounds. Our rapid discovery and evolution of custom-designed enzymes enables breakthrough developments for sustainable production of ingredients for pharmaceuticals, cosmetics, chemical, food and beverages.
We’re hiring a highly capable Machine Learning Engineer into our Data team. This team is responsible for developing and implementing state-of-the-art approaches for evolving enzymes and microbes to enhance the production of chemicals and natural compounds. The engineer will integrate the development of our cloud-based artificial intelligence platform for enhancing Allozymes’ enzyme optimization capabilities. Working in a highly collaborative and dynamic environment, this role has the opportunity to interact with other scientists, automation and process engineers to achieve these goals.
- Contribute to the design and improvement of Allozymes cloud-based AI platform.
- Scope project requirements, assess data quality, process data and perform feature engineering.
- Build, train and deploy ML/DL models, using state-of-the-art technologies and proprietary data to accurately perform predictions and generate new, high performing, enzymes.
- Perform model evaluation and statistical analysis to improve model quality.
- Enhance the performance and deployment environment of implemented solutions.
Requirements & Qualifications
- MS or PhD in mathematics, statistics, computer science, engineering or a related quantitative field with a focus on AI and Machine Learning.
- 2+ years of relevant industry experience.
- Expertise in building, training and deploying Machine and Deep Learning models.
- Proficiency in Python.
- Expertise in using ML/DS specific python libraries (Pandas, Numpy, Scipy, Scikit-learn, PyTorch, Keras).
- Experience with ML life-cycle management and code/data version control tools.
- Familiarity working with Cloud computing.
- Ability to work in a fast-paced, collaborative and cross-functional environment and communicate results effectively to management.
- Experience with supervised and unsupervised learning algorithms, clustering, feature selection methods, evaluation, dimensionality reduction, Bayesian inference, hyper-parameter tuning and model optimization is a plus
- Experience with Language models, Encoders, Transformers, Attention, Generative models and GANs is a plus
- Experience in biology, bioinformatics or computational biology.
- Experience using AWS/SageMaker is a plus
- Experience with containers and container orchestration tools is a plus
- Experience writing production-ready code (version-controlled, scalable, well-documented, testable, deployment-ready) is a plus
Candidates who fulfill the above-mentioned criteria are encouraged to Apply here