Machine Learning Researcher - Agentic Science
Remote • Remote • Full-time
Posted 19d ago
Job Location
Remote
Tech Stack
Remote Work Policy
Fully remote
Employment Type
Full-time
Categories
Machine Learning Engineer
About the job
PostEra is seeking a Machine Learning Researcher to spearhead the development of an agentic research vertical. This role involves leveraging agentic systems to automate the creation of mechanistic models for biochemical and physiological processes, and to analyze biological data for target validation. You will collaborate closely with chemists and biologists to guide drug discovery decisions using these models. A key focus will be on developing machine learning methods capable of rapid adaptation to new drug discovery challenges with limited labeled data, particularly in molecular and tabular in-context learning and building foundation models from proprietary multimodal data. You will be responsible for the entire research loop, from defining tasks and constructing datasets to training and scaling models, performing rigorous ablations, and translating successful methods into practical capabilities for PostEra's scientists. While prior drug discovery experience is not mandatory, a strong motivation to learn the domain and collaborate with interdisciplinary scientists is essential.
Responsibilities
- Develop and benchmark agentic systems for automating quantitative model development and biological data analysis.
- Independently identify, formulate, and lead research projects in areas like in-context learning, agentic systems, few-shot adaptation, tabular foundation models, and molecular machine learning.
- Design and train models that adapt to new assays, endpoints, targets, or chemical series using limited labeled context and historical data.
- Rigorously compare new approaches against strong baselines and curate test cases to deconfound bias.
- Collaborate with scientists to align modeling objectives and evaluation metrics with practical drug discovery decisions.
- Develop efficient training and data pipelines and scale models across molecular and tabular tasks.
- Produce readable, reproducible research code, maintain tracked experiments, and contribute through code review and documentation.
- Publish research results in leading venues and represent PostEra within the scientific community.
Requirements
- PhD in machine learning or a STEM field involving novel machine learning approach development.
- Track record of high-quality research, including publications and open-source contributions.
- Strong research or engineering experience in modern ML, deep learning, or statistical modeling, with theoretical understanding.
- Demonstrated expertise in at least one of: agentic workflows for science, ML for bioinformatics/clinical data modeling, in-context learning, tabular learning, or few-shot learning.
- Hands-on experience training, debugging, and evaluating ML models in Python using frameworks like PyTorch or JAX.
- Ability to translate ambiguous scientific/technical problems into well-defined ML projects.
- Ability to design careful experiments, benchmarks, and ablations to distinguish improvements from biases.
- Comfort working in a startup environment with evolving priorities and imperfect data.