PostEra
PostEra
PostEra yangi dori vositalarini kashf etish usullarini takomillashtirishga e’tibor qaratadigan biotexnologiya va sun’iy intellekt kompaniyasidir. Uning Proton platformasi mashinaviy o‘qitishni tibbiy kimyoga tatbiq etib, tadqiqotchilarga dori vositalarini izlashdagi murakkab muammolarni hal qilish va istiqbolli davolash usullarini ishlab chiqishni tezlashtirishga yordam beradi. 2020-yilda tashkil etilgan PostEra Pfizer va Amgen kabi farmatsevtika tashkilotlari bilan dori ishlab chiqishda sun’iy intellektga asoslangan yondashuvlar ustida hamkorlik qiladi.

Machine Learning Researcher, Agentic Science at PostEra (Remote)

PostEra is seeking a Machine Learning Researcher to build agentic systems and adaptive models for AI-driven biotechnology. The role applies computational methods to medicinal chemistry and drug discovery.

Tavsif

  • Build PostEra’s agentic research function by automating mechanistic modeling of biochemical and physiological processes
  • Analyze biological data for target validation and inform drug discovery decisions with machine learning models
  • Create machine learning methods that adapt to new drug discovery challenges with limited labeled data
  • Develop molecular and tabular in-context learning systems and foundation models using proprietary multimodal data
  • Assess relevant prior examples and tasks, measure when transfer helps or harms, and deliver reliable predictions under distribution shift
  • Define tasks, build datasets and evaluation episodes, establish baselines, train and scale models, run rigorous ablations, and translate effective methods into scientific capabilities
  • Develop and benchmark agentic systems for quantitative biological and physiological modeling
  • Lead independent research projects in 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, and chemical series
  • Evaluate methods against strong baselines and create test cases that account for bias sensitivity
  • Work with scientists on potency modeling, ADME prediction, selectivity, lead optimization, and early clinical study design
  • Build efficient training and data pipelines while scaling models across molecular and tabular problems
  • Write readable, reproducible research code; document experiments; and support code review and shared modeling infrastructure
  • Publish findings in leading machine learning, medicinal chemistry, or computational biology venues and represent PostEra within the scientific community

Talablar

  • PhD in machine learning or in a STEM research field focused on developing novel machine learning methods
  • Evidence of high-quality research through publications, open-source contributions, or comparable work
  • Strong research or engineering background in modern machine learning, deep learning, or statistical modeling, with a solid grasp of algorithmic theory
  • Expertise in at least one relevant area, including agentic scientific workflows, machine learning for bioinformatics or clinical data, in-context learning, tabular learning, or few-shot learning
  • Practical experience training, debugging, and evaluating machine learning models in Python with frameworks such as PyTorch or JAX
  • Ability to turn ambiguous scientific or technical questions into well-defined machine learning projects with datasets, tasks, baselines, metrics, and validation plans
  • Ability to design rigorous experiments, benchmarks, and ablations that separate genuine gains from bias and identify the sources of model improvements
  • Comfort working in a startup where priorities change, data may be imperfect, and sound judgment is as important as model complexity
  • Drug discovery experience is not required
  • Preferred: experience training tabular foundation models for sparse, heterogeneous, small-data, or high-missingness settings
  • Preferred: experience developing molecular in-context learning systems or adapting general-purpose in-context models to molecular or scientific data
  • Preferred: experience training large models, including 1B-plus parameter systems, distributed training, sharding, data and model parallelism, and large-scale data pipelines
  • Preferred: experience developing AI co-scientist systems for physical or biological problems
  • Preferred: hands-on machine learning experience with biological, biochemical, or clinical data
  • Preferred: experience moving research models into production scientific software or computational workflows

Imtiyozlar

  • Equity allocation of 0.05% to 0.1%
  • Compensation adjusted proportionally
  • Recognition within the organization
  • Opportunities for meaningful promotion

O‘xshash ish o‘rinlari

The Walt Disney Company

Principal Software Engineer, Video Coding and Media Processing

The Walt Disney Company

Lead research and development in video coding, media processing, and AI-driven streaming at Disney. Shape technical standards, platform architecture, and long-term product strategy.

Ochish
Capital One

Senior Full-Stack Engineer, Mainframe and Cloud Resilience

Capital One

Lead engineering work to modernize Capital One’s IBM mainframe systems and strengthen cloud operations. Build resilient software with Agile teams using AWS and related technologies.

Ochish
The Walt Disney Company

Software Engineer II, ML Observability

The Walt Disney Company

Build machine learning anomaly detection and observability systems for Disney+, Hulu, and ESPN. Develop production models, telemetry pipelines, inference services, and AI-powered operational insights.

Ochish
The Walt Disney Company

Software Engineer II, Ad Platform CRM Analytics

The Walt Disney Company

Build Salesforce CRM Analytics applications for Disney’s advertising platforms. Develop scalable, secure web solutions spanning media, sports, news, and entertainment.

Ochish
The Walt Disney Company

Principal Software Engineer, Video Coding and Streaming

The Walt Disney Company

Lead research and development in video coding, processing, and streaming, with a focus on machine learning and AI. Shape platform architecture, contribute to industry standards, and advance technical work across Disney’s global team.

Ochish