Technical Associate, Annotation and Proofreading

This is a hands-on role checking and correcting what our automated reconstruction produces. You will annotate and proofread microscopy volumes of brain tissue: tracing neurons, marking synapses and other structures, and fixing the errors that automated segmentation makes. Your annotations become the ground truth that our models train on and are measured against, so care and consistency come first, and speed follows.

You report to the Head of Computation and work closely with the scientists and engineers who build our models and annotation tools, using logic and evidence to advance your work so as to boost the performance of all. You will also work closely with the software engineering team to develop and refine tools and infrastructure to streamline data annotation.

This is the first data annotation role  the start, you will do the annotation yourself and help define how it is done: the protocols, the quality checks, and the training material. As the work grows, we expect this role to grow into leading an annotation team, which means training new annotators, assigning work, and tracking quality and throughput. The job also requires systematic documentation, analysis, and iterative problem solving, to arrive at working protocols, apply them, and share them.

• Annotate and proofread 3D microscopy volumes of brain tissue: trace neurons, label synapses and other structures, and fix split and merge errors in automated segmentation.
• Write and maintain annotation protocols, with examples of hard cases, so that two annotators make the same call on the same data.
• Run quality control: review annotations, measure agreement between annotators, and keep gold-standard sets for training and checking.
• Track throughput and error rates and use basic statistics to report where time goes and where quality varies.
• Tell the tool and model teams what slows annotation down and which errors the models make most often.
• As the team grows, you will be instrumental in training and onboarding new annotators, assign and review their work, and assist in recruitment efforts for future team members.
• Documentation and training: keep protocol records that others can execute, with the reasoning behind each decision.

The disorders of the brain affect over 1, people around the world:
Alzheimer’s, Parkinson’s, stroke, and other conditions. We operate with a sense of urgency, even as we look to understand the brain at its most fundamental levels.

We are hypercollaborative, and focused on impact over short-term markers of productivity. Creativity and failure are the stepping stones to scale, and working together with “strong opinions, weakly held” is our style.

We solve real engineering problems the best way we can: inventing fast when we have to, and using good existing solutions where they exist. We believe hard problems only yield to many disciplines working together, so collaboration is required, not optional.

We expect people to explore the unknown, which means making mistakes daily, owning them, and learning from them to improve and excel.

We are recruiting a team of scientists and engineers who exemplify all these values.

• B.S. or B.A. in neuroscience, biology, biomedical engineering, computer science, or a related field, or equivalent experience.
• Direct hands‑on experience with careful visual work on images or data, such as image annotation, histology, microscopy, or data labeling.
• Ability to apply a written protocol consistently, and to notice and report when a case falls outside it.
• Basic quantitative skills: spreadsheets, simple statistics, and reading a chart.
• Excellent attention to detail and scientific rigor.

• Experience with neuron tracing, connectomics proofreading, or volumetric…