Episteme
Postdoctoral Researcher (Machine Learning for Neural Circuit Modeling)
Episteme, San Francisco, California, United States, 94199
Postdoctoral Researcher (Machine Learning for Neural Circuit Modeling)
Join us to apply for the
Postdoctoral Researcher (Machine Learning for Neural Circuit Modeling)
role at
Episteme .
Location: San Francisco, CA, USA (On-site). Start date: ASAP. Duration: Initial appointment is for 1 year, with extensions (up to a total of 3 years) contingent upon performance.
We are inviting applications for a Postdoctoral Researcher position in machine learning applied to large‑scale neural activity datasets. This role is central to our program to decode and model C. elegans neural dynamics by integrating experimental recordings with predictive computational frameworks.
Episteme is a new type of R&D company based in San Francisco. We identify, hire, and bring together exceptional scientific researchers across disciplines and geographies—especially individuals who want to pursue difficult and important problems that do not fit into the purview of traditional institutions. Our aim is to create a new path separate from academia, industry, and government for enabling, translating, and commercializing science into tangible impact.
Overview: As a Postdoctoral Researcher, you will lead the development of statistical and machine learning models that predict and explain neural dynamics from experimental recordings. You will work closely with experimentalists to analyze calcium/voltage imaging data, design prospective validation experiments, and develop models that move beyond prediction toward causal understanding. This role is ideal for individuals with strong ML foundations and a deep interest in neuroscience.
Research Focus Areas:
Predictive modeling of neural activity using high‑dimensional optical recordings
Statistical inference and causal analysis of circuit‑level dynamics
Integration of multimodal priors (imaging, behavior, connectomics) into unified models
Development and application of advanced ML approaches (e.g. graph neural networks, symbolic regression, interpretable models, probabilistic modeling)
Mathematical formalism to connect learned models with mechanistic circuit hypotheses
Key Responsibilities:
Develop and test machine learning models for predicting neural activity and behavior from experimental datasets
Apply statistical and causal inference methods to identify candidate circuit mechanisms
Collaborate with experimental postdocs to design validation protocols and integrate multimodal data sources
Explore advanced modeling frameworks (e.g. symbolic regression, GNNs, probabilistic generative models) to enhance interpretability and formal grounding
Publish results in top‑tier journals and present at major conferences
Contribute to the collaborative, interdisciplinary environment of the project
Follow a structured research plan, with defined tasks and milestones
Qualifications:
Ph.D. in Computer Science, Applied Mathematics, Computational Neuroscience, or a related field
Strong track record of research in machine learning applied to neural data or other high‑dimensional biological datasets
Demonstrated expertise in statistical modeling, predictive analysis, and causal inference
Experience with advanced ML methods such as graph neural networks, probabilistic models, or symbolic regression
Interest in interpretability and connecting data‑driven results to mechanistic understanding
Proficiency in scientific programming (Python, PyTorch/JAX, or similar frameworks) and collaborative software development practices
Strong written and verbal communication skills
Ability to work both independently and as part of an interdisciplinary team
Motivation to tackle ambitious, high‑risk/high‑reward problems at the frontier of neuroscience and AI
Application Instructions: To apply, please upload the following materials along with your application in Ashby:
Curriculum vitae, including a list of publications
A statement (max 2 pages) describing your research interests, experience with activity imaging, and your most significant scientific contribution to date
At least two (up to four) letters of recommendation (to be uploaded directly by letter writers to the link provided after application submission)
We strongly encourage early submissions. Positions will remain open until filled. For questions, please contact Dr. Michael Skuhersky at recruiting@episteme.com.
Additional Information: In addition to competitive salaries, Episteme offers a comprehensive benefits package. You will be part of a collaborative effort bridging neuroscience, machine learning, and advanced imaging, with opportunities for high‑impact publications and career advancement.
#J-18808-Ljbffr
Postdoctoral Researcher (Machine Learning for Neural Circuit Modeling)
role at
Episteme .
Location: San Francisco, CA, USA (On-site). Start date: ASAP. Duration: Initial appointment is for 1 year, with extensions (up to a total of 3 years) contingent upon performance.
We are inviting applications for a Postdoctoral Researcher position in machine learning applied to large‑scale neural activity datasets. This role is central to our program to decode and model C. elegans neural dynamics by integrating experimental recordings with predictive computational frameworks.
Episteme is a new type of R&D company based in San Francisco. We identify, hire, and bring together exceptional scientific researchers across disciplines and geographies—especially individuals who want to pursue difficult and important problems that do not fit into the purview of traditional institutions. Our aim is to create a new path separate from academia, industry, and government for enabling, translating, and commercializing science into tangible impact.
Overview: As a Postdoctoral Researcher, you will lead the development of statistical and machine learning models that predict and explain neural dynamics from experimental recordings. You will work closely with experimentalists to analyze calcium/voltage imaging data, design prospective validation experiments, and develop models that move beyond prediction toward causal understanding. This role is ideal for individuals with strong ML foundations and a deep interest in neuroscience.
Research Focus Areas:
Predictive modeling of neural activity using high‑dimensional optical recordings
Statistical inference and causal analysis of circuit‑level dynamics
Integration of multimodal priors (imaging, behavior, connectomics) into unified models
Development and application of advanced ML approaches (e.g. graph neural networks, symbolic regression, interpretable models, probabilistic modeling)
Mathematical formalism to connect learned models with mechanistic circuit hypotheses
Key Responsibilities:
Develop and test machine learning models for predicting neural activity and behavior from experimental datasets
Apply statistical and causal inference methods to identify candidate circuit mechanisms
Collaborate with experimental postdocs to design validation protocols and integrate multimodal data sources
Explore advanced modeling frameworks (e.g. symbolic regression, GNNs, probabilistic generative models) to enhance interpretability and formal grounding
Publish results in top‑tier journals and present at major conferences
Contribute to the collaborative, interdisciplinary environment of the project
Follow a structured research plan, with defined tasks and milestones
Qualifications:
Ph.D. in Computer Science, Applied Mathematics, Computational Neuroscience, or a related field
Strong track record of research in machine learning applied to neural data or other high‑dimensional biological datasets
Demonstrated expertise in statistical modeling, predictive analysis, and causal inference
Experience with advanced ML methods such as graph neural networks, probabilistic models, or symbolic regression
Interest in interpretability and connecting data‑driven results to mechanistic understanding
Proficiency in scientific programming (Python, PyTorch/JAX, or similar frameworks) and collaborative software development practices
Strong written and verbal communication skills
Ability to work both independently and as part of an interdisciplinary team
Motivation to tackle ambitious, high‑risk/high‑reward problems at the frontier of neuroscience and AI
Application Instructions: To apply, please upload the following materials along with your application in Ashby:
Curriculum vitae, including a list of publications
A statement (max 2 pages) describing your research interests, experience with activity imaging, and your most significant scientific contribution to date
At least two (up to four) letters of recommendation (to be uploaded directly by letter writers to the link provided after application submission)
We strongly encourage early submissions. Positions will remain open until filled. For questions, please contact Dr. Michael Skuhersky at recruiting@episteme.com.
Additional Information: In addition to competitive salaries, Episteme offers a comprehensive benefits package. You will be part of a collaborative effort bridging neuroscience, machine learning, and advanced imaging, with opportunities for high‑impact publications and career advancement.
#J-18808-Ljbffr