Machine Learning Researcher – Agentic Science

PostEra

. Develop the agentic research vertical at PostEra using agentic systems to automate development of mechanistic models for biochemical and physiological processes .

Posted 10/5/2026full-timeRemote • United StatesMid-LevelSenior💰 $200,000 - $300,000 per yearWebsite

Core Competencies

Role fit

Core Competencies

Use this summary to align your resume positioning with the role.

Demonstrates expertise in developing and applying machine learning methods for drug discovery, including in-context learning and agentic systems. Proficient in designing experiments, training models, and translating complex scientific problems into actionable ML projects.

Highest-signal resume keywords

PhD In Machine LearningMachine Learning Approaches To BioinformaticsPython ProgrammingExperience With PyTorch Or JAXAgentic Workflows For Science

ATS Keywords

Tailor your resume

Applicant Tracking System Keywords

Tip: use these terms in your resume and cover letter to boost ATS matches.

Hard Skills

Machine LearningDeep LearningStatistical ModelingIn-Context LearningTabular LearningFew-Shot LearningModel TrainingModel EvaluationData Pipeline DevelopmentExperimental Design

Soft Skills

Independent ResearchProblem-SolvingCollaborationAdaptabilityJudgment

Tools & Technologies

PyTorchJAXData ParallelismModel ParallelismLarge-Scale Data Pipelines

Industry Keywords

Drug DiscoveryBiochemical Data ModelingClinical Data ModelingQuantitative Biological ModelsMolecular Machine Learning

Tech Stack

Tools & technologies

PythonPyTorch

About the role

Key responsibilities & impact

Develop the agentic research vertical at PostEra using agentic systems to automate development of mechanistic models for biochemical and physiological processes
Analyse biological data for target validation and use models to drive drug discovery decisions
Develop machine learning methods that adapt to new drug discovery problems from limited labeled data
Build molecular and tabular in-context learning systems and foundation models from proprietary multimodal data
Determine relevant prior examples and tasks, quantify when transfer is helpful or harmful, and provide reliable predictions under distribution shift
Define tasks, construct datasets and evaluation episodes, develop baselines, train and scale models, perform rigorous ablations, and translate successful methods into capabilities used by scientists
Develop and benchmark agentic systems for quantitative biological and physiological models
Independently identify, formulate, and lead research projects involving in-context learning, agentic systems, few-shot adaptation, tabular foundation models, and molecular machine learning
Design and train models adapting to new assays, endpoints, targets, or chemical series
Rigorously compare approaches against strong baselines and curate bias-sensitive test cases
Collaborate with scientists on potency modeling, ADME prediction, selectivity, lead optimization, and early clinical study design
Develop efficient training and data pipelines and scale models across molecular and tabular tasks
Produce readable, reproducible research code; track experiments; contribute to code review, documentation, and shared modeling infrastructure
Publish results in leading machine learning, medicinal chemistry, or computational biology venues and represent PostEra to the scientific community

Requirements

What you’ll need

PhD degree in machine learning, or STEM research involving the development of novel machine learning approaches
Track record of high-quality research, such as publications and open-source contributions
Strong research or engineering experience in modern machine learning, deep learning, or statistical modeling, backed by understanding of the theory behind machine learning algorithms
Demonstrated expertise in at least one relevant area: agentic workflows for science, machine learning approaches to bioinformatics and clinical data modelling, in-context learning, tabular learning, few-shot learning
Hands-on experience training, debugging, and evaluating ML models in Python using frameworks such as PyTorch or JAX
Ability to independently translate ambiguous scientific or technical problems into well-defined ML projects, including datasets, task definitions, baselines, metrics, and validation schemes
Ability to design careful experiments, benchmarks, and ablations that distinguish improvements from biases, and understand which aspects of the model led to the improvements
Comfort working in a startup environment where priorities evolve, data is imperfect, and high-quality judgment matters as much as raw model complexity
Prior drug discovery experience is not required
Nice-to-have: experience training tabular foundation models, particularly for sparse, heterogeneous, small-data, or high-missingness settings
Nice-to-have: developing molecular in-context learning systems or adapting general-purpose in-context models to molecular or scientific data
Nice-to-have: large model training, including 1B+ parameter models, distributed training, sharding, data parallelism, model parallelism, and large-scale data pipelines
Nice-to-have: development of AI “co-scientist” systems for physical or biological problems
Nice-to-have: hands-on experience modelling biological, biochemical or clinical data using machine learning approaches
Nice-to-have: moving research models into production scientific software or computational workflows

Benefits

Comp & perks

Equity: 0.05 - 0.1%
Proportional compensation
Internal recognition
Meaningful promotions