Назад
Company hidden
2 дня назад

AI Engineer - Connectomics Pipelines (AI)

128 050 - 239 789$
Формат работы
onsite
Тип работы
fulltime
Грейд
middle/senior
Английский
b2
Страна
US
Вакансия из списка Hirify.GlobalВакансия из Hirify Global, списка международных tech-компаний
Для мэтча и отклика нужен Plus

Мэтч & Сопровод

Для мэтча с этой вакансией нужен Plus

Описание вакансии

Текст:
/
TL;DR
AI Engineer - Connectomics Pipelines (AI): Building and deploying production-ready pipelines for segmenting, proofreading, and reconstructing connectomes from expansion microscopy data with an accent on deep learning, large-scale volumetric processing, and reconstruction quality. Focus on training and fine-tuning vision models, optimizing GPU-cluster inference, designing rigorous evaluations, and delivering reproducible pipelines for scientific use.

Location: On-site at Janelia Research Campus, 19700 Helix Drive, Ashburn, Virginia, United States

Annual compensation: $128,050.62–$160,063.28 for AI Engineer II; $155,495.81–$194,369.76 for AI Engineer III; $191,831.74–$239,789.68 for AI Engineer IV.

Company

hirify.global’s Janelia Research Campus is a life-sciences research center developing collaborative scientific methods, tools, and technologies.

What you will do

  • Reconstruct connectomes at scale from expansion microscopy data using pretrained segmentation models.
  • Train and fine-tune models as new ground-truth data becomes available.
  • Design and run rigorous evaluations to improve reconstruction quality.
  • Optimize inference throughput on GPU clusters and support high-throughput processing.
  • Build proofreading workflows, including integrations such as CAVE, and coordinate annotation efforts.
  • Release reproducible pipelines, models, and reconstructions while collaborating with microscopists, biologists, neuroscientists, and computer scientists.

Requirements

  • At least three years of experience training and evaluating deep learning models, including Transformers or U-Nets, ideally on 3D image data.
  • Experience deploying models with workflow orchestration and high-throughput GPU-cluster processing using tools such as Kubernetes, Nextflow, or LSF.
  • Strong Python skills with PyTorch or JAX.
  • Familiarity with modern vision models such as DINOv3, SAM, Cellpose, and Vision Transformers.
  • Ability to explain model behavior, understand the effects of architecture and regularization choices, and design experiments to test hypotheses.
  • Ability to define reconstruction-quality benchmarks and evaluate changes against them.
  • Master’s degree, PhD, or equivalent combination of education and experience.
  • Experience with shared codebases and git-based collaboration.
  • Interest in learning neuroscience and cell biology and working across disciplines.

Nice to have

  • Experience with microscopy image analysis, especially 3D electron or expansion microscopy.
  • Knowledge of Flood-Filling Networks, Local Shape Descriptors, and graph agglomeration.
  • Experience with CAVE, Neuroglancer, and Zarr.
  • Experience with self-supervised methods such as DINO or masked autoencoders.
  • Experience working with large biological datasets.

Culture & Benefits

  • Full-time individual-contributor role within Scientific Computing, with potential opportunities to mentor junior engineers.
  • On-site work at Janelia Research Campus is required.
  • Comprehensive health and welfare benefits, retirement plans, time off, and wellness programs.
  • Access to large-scale computational infrastructure, high-quality datasets, and interdisciplinary AI and scientific teams.
  • On-site childcare, free gyms, on-campus housing, social and dining spaces, and shuttle service from the Washington, D.C. metro area.

Hiring process

  • Submit a one- to two-page cover letter describing qualifications and relevant experience.
  • Describe a personally executed deep learning project, preferably involving a Vision Transformer, U-Net, or diffusion model; include code links where possible, individual contributions, results, limitations, and challenges.
  • Write the letter yourself and include a GitHub profile, personal website, or relevant project link at the bottom.

Будьте осторожны

Если работодатель просит войти в их систему, используя iCloud/Google, прислать код/пароль, запустить код/ПО, не делайте этого. Это мошенники. Обязательно жмите «Пожаловаться» или пишите в поддержку. Подробнее в гайде →