Backend Engineer Visa Sponsorship Jobs in Maine

Job Summary

The Kumar Lab studies the genetic and neurological basis of behavior with the goal of therapeutic and mechanistic discovery. We leverage machine learning and computer vision methods to model human diseases by transforming videos of mice into quantitative behavioral traits. Technology developed by our lab has been deployed in the JAX Envision System, a home cage monitoring platform. Envision streams continuous petabyte-scale video from animal housing into a cloud archive and operates on it in close to real time using multi-task algorithms. Segmentation, pose estimation, and instance assignment are all used for action recognition, action localization tasks using supervised and unsupervised approaches to quantify complex animal behaviors representative of health and disease.

As a Scientific Software Engineer, you will collaboratively shape the machine learning and computer vision engineering behind digital measures, harden pre-existing algorithms, and leverage robust MLOps principles. You will follow technical direction, mentor trainees, and drive publications and model releases that come out of the work.

A successful candidate will be independently motivated, work collaboratively, and contribute meaningfully to the development of therapeutics for neurodevelopmental and neuropsychiatric disorders.

The Challenges

Mice are inherently difficult to study because they tend to avoid detection. As highly flexible, deformable animals, they are primarily active in low-light conditions and occupy small, confined spaces. These behaviors create significant challenges for computer vision tasks such as segmentation, pose estimation, instance tracking and identity tracking.

• Human Annotation is Expensive. Expert behaviorists’ time is limited, so creating a system that enables quick, high impact, scalable annotation is a must.
• Occlusion Complicates Behavior Annotation. Group-housed mice huddle and occlude each other.
• Models Must Generalize. Measures must perform across a diversity of genetic backgrounds, environments, coat colors, and sites, and across an archive too large to easily reprocess. Continual learning, edge-case mining, and efficient deployment are critical. You will be working with messy real-world data.

Minimum Requirements

Education: Bachelor's required

Experience: 3 years required/5 years preferred

Key Responsibilities and Essential Functions

Responsibility

Time Allocation

• 70% - Design, train, and deploy computer vision and machine learning models and the pipelines around them, from stated aims through production, working with direction from project sponsors/PIs and senior team members. Write code other people can read, run, and extend. Contribute to the publications and open-source releases that come out of these projects.
• 20% - Evaluate models: quantify how measures hold up across strain, rig, and site. Assess new methods and architectures against our problems and report what actually survives the comparison.
• 10% - Collaborate with lab members, review code, document what you build, and invest in your own technical growth.

What You're Good At

• Depth in machine learning. A master's degree in computer science, machine learning, or a related field is preferred; a BS or BA with equivalent demonstrated experience is considered. Either way we expect roughly three years of hands-on work and the ability to judge whether a method applies to our problem, implement it, and explain its performance.
• Proficiency leveraging LLM-based coding assistants (e.g., GitHub Copilot, Claude Code) to accelerate development, while maintaining rigorous standards for code quality, correctness, and maintainability.
• Production machine learning. PyTorch, training and evaluation infrastructure, model versioning, and deployment — including quantization and runtime optimization for edge inference — plus the data plumbing that carries video at volume (object storage, containers, Kubernetes, SLURM, Go, Bash).
• Working familiarity with technologies such as Python, PyTorch, ffmpeg, C++, Cython, SQLite, PostgreSQL, SLURM, Bash, as well as cloud providers and technologies like GCP, AWS. Specialized expertise in machine learning and machine learning frameworks and tools.
• Judgment about prioritization. This role demands that an individual balance competing priorities across scientific, engineering, and deadline driven requirements.
• Excellent oral and written communication. You will explain complex technical trade-offs to biologists, to institutional stakeholders, and to external collaborators, and you will contribute to manuscripts. You proactively elicit feedback, are comfortable explaining your work to scientists, and encourage discussion.
• Engagement with your work and a track record of productivity. Background in biological sciences, or a real appetite to learn the domain.

To Apply

Send a CV and one paragraph that names which of the problems above interests you and points at one thing you have built, with a link. If your work involves video or behavior, tell us how you split train and test, and why.

Pay Range: $85,987 - $143,962, pay is determined by years of experience.

About JAX:

The Jackson Laboratory is an independent, nonprofit biomedical research institution with a National Cancer Institute-designated Cancer Center and nearly 3,000 employees in locations across the United States (Maine, Connecticut, California), Japan and China. Its mission is to discover precise genomic solutions for disease and empower the global biomedical community in the shared quest to improve human health.

Founded in 1929, JAX applies over nine decades of expertise in genetics to increase understanding of human disease, advancing treatments and cures for cancer, neurological and immune disorders, diabetes, aging and heart disease. It models and interprets genomic complexity, integrates basic research with clinical application, educates current and future scientists, and provides critical data, tools and services to the global biomedical community.

EEO Statement:

The Jackson Laboratory provides equal employment opportunities to all employees and applicants for employment in all job classifications without regard to race, color, religion, age, mental disability, physical disability, medical condition, gender, sexual orientation, genetic information, ancestry, marital status, national origin, veteran status, and other classifications protected by applicable state and local non-discrimination laws.