AI Research Engineer, Multiomics and Imaging

Position Summary:

Build the computational infrastructure for discovering how cells organize into tissues.

The Biological Information Architecture (BIA) Lab, led by Dr. Felix Zhou at Vanderbilt University, seeks a strong, self-motivated Research Engineer to help build the software, AI workflows, and computational methods that will power a new generation of biological discovery.

This is not a conventional academic programming role. You will have substantial ownership over the lab’s technical direction: architecting software from the ground up, building agentic AI systems for scientific analysis, developing new computational methods, and turning promising ideas into robust tools used by researchers.

We are interested in strong software engineers from industry, computationally exceptional undergraduate or master’s students, and quantitative scientists who want to work on genuinely difficult scientific problems. We care more about technical ability, curiosity, and evidence that you can build things than academic qualifications.

You will also contribute to publications and grants, help establish engineering practice, mentor trainees, and help identify technologies with potential for open-source release, licensing, or commercialization.

This position is a term position. A term position is a staff appointment established for a defined period of time based on the operational needs of the business unit and Vanderbilt University, generally expected to exceed six months but not extend beyond one year. This position's incumbent will be evaluated at the end of a one year assignment for renewal.

About the Work Unit:

The BIA Lab is a new, interdisciplinary computational biology group built around a founding north star mission: “develop the computational tools to decode and ultimately help reprogram the rules governing how individual cells determine tissue-scale behavior”. The lab pursues this objective through atlas-scale multimodal data analysis: combining advanced microscopy, quantitative cell phenomics, spatial tissue profiling and multi-omics data; first-principles open-minded, curiosity-driven scientific inquiry integrating ideas across disciplines without borders, be it theoretical physics, philosophy, economics, biology, computing or mathematics.

We work closely with an expansive network of internal and external collaborators, and committed to open, well-engineered software for the wider bioimage-analysis and computational biology community. The lab is based in Vanderbilt’s Department of Cell and Developmental Biology and affiliated with the Center for Computational Systems Biology (CCSB), a trans-institutional center spanning Vanderbilt Basic Sciences, Vanderbilt University Medical Center, and the College of Connected Computing, placing the lab within a growing community of computational biologists, imaging scientists, and systems-level researchers on campus.

Though newly launched, the lab has a strong methods track record. We have released a suite of open-source tools used by the community, including u-Segment3D (3D cell segmentation); u-Unwrap3D (geometric computing), u-Protrude3D (surface protrusion analysis), SAM-SPOT and MOSES (phenotyping and motion quantification), and v-InfoTrace (information-flow analysis in images). The opportunity now, with real ownership, is to connect and build these cell-level tools into scalable workflows to reverse-engineer the logic circuitry of tissue signaling.

BIA lab website: https://bia-lab-team.github.io/BIA_Lab_Website/index.html

BIA lab GitHub: https://github.com/BIA-Lab-Team

BIA lab publications: https://bia-lab-team.github.io/BIA_Lab_Website/publications.html

Why Join:

• Direct influence over software architecture, tooling choices, and engineering culture from day one

• Work at the frontier of agentic AI applied to multi-omics and imaging science, with substantial latitude to prototype and ship your own ideas

• Solve real scientific problems involving large, messy, multimodal datasets

• Work closely with the PI on scientific and technical direction in a high-trust environment with substantial autonomy.
• Build tools that enable non-expert researchers to run sophisticated analyses at scale.
• Shape your own growth path toward technical leadership, scientific software, AI systems, computational biology, or technology development.
• Potential opportunities for open-source releases, technology transfer, licensing, or spin-out development as promising technologies mature.

• Join an interdisciplinary environment without borders where ideas from computing, mathematics, physics, biology, arts and philosophy can directly shape the work.

Key Functions and Expected Performance:

Shape the lab’s technical vision and roadmap

• Define software architecture, development standards, and infrastructure choices for the lab

• Advise the PI on build-vs-adopt decisions and long-term technical strategy

Design and development of agentic workflows for multi-omics and imaging data

• Build agentic, LLM-based pipelines that automate ingestion, quality control, processing, and analysis of multi-omics (genomics, transcriptomics, proteomics) and imaging (light-sheet, high-content, spatial) data

• Integrate agentic workflows with existing lab software and HPC/cloud compute infrastructure

Evaluation, integration, and potential commercialization of new methodologies and tools

• Research and assess suitability of emerging methodologies, algorithms, and open-source packages relevant to the lab’s research direction

• Turn promising research ideas into reliable, reusable software.

• Identify lab-developed technologies with translational or commercial potential and support early-stage technology-transfer, licensing, or spin-out discussions.

Teaching, onboarding, and community engagement

• Onboard and train graduate students, postdocs, and rotation students on lab software and computational workflows.
• Promote and communicate the lab’s software through open-source releases, conferences, GitHub, forums, workshops, and other community channels.
• Contribute to publications and grant writing

Experience and Skills:

Necessary

• Strong software development and technical ability through research, open-source work, internships, industry experience, competitions, or substantial independent projects.

• A bachelor’s degree in a relevant scientific or computational field is sufficient; exceptional candidates with unconventional backgrounds are encouraged to apply.

• Strong Python skills and familiarity with scientific libraries such as NumPy, SciPy, pandas, scikit-image, or scikit-learn.

• Experience developing, releasing, and maintaining software projects.

• Experience with, or strong interest in developing, agentic and LLM-based workflows (e.g., Claude Agent SDK, LangChain, or similar frameworks).

• Strong communication skills and the ability to work effectively with technical and non-technical colleagues.

• Self-motivated, enterprising, intellectually curious, and comfortable operating with an incompletely specified roadmap.

Preferred

• Experience with multi-omics data types (genomics, transcriptomics, proteomics) and/or bioimage analysis (light-sheet, high-content, or spatial imaging).

• Knowledge of workflow orchestration and parallel/distributed computing technologies (e.g., Snakemake, Nextflow, NVIDIA CUDA, OpenMPI, or cloud-based HPC).

• Experience with production-scale software engineering, scientific computing, or large-scale data systems.

Education and Certifications:

• Bachelor’s degree in a relevant scientific or computational field with strong computational emphasis.

• A minimum of 1–2 years of postgraduate or industry experience in software engineering, software development, or a related field is required.

• Exceptional undergraduate and master’s candidates are encouraged to apply, particularly those with substantial software-building experience.

• Master’s or PhD preferred but not required.

• Architect and develop end‑to‑end software platforms for multiomics and imaging data analysis.
• Design and implement agentic AI systems that automate scientific hypothesis generation and testing.
• Create scalable computational pipelines for high‑throughput cellular and tissue data.
• Collaborate with biologists to translate experimental needs into technical solutions.
• Write production‑grade code, documentation, and automated tests.
• Contribute to scientific manuscripts, grant applications, and conference presentations.
• Establish and enforce best engineering practices within the lab.
• Mentor undergraduate, graduate, and postdoctoral trainees in software development.
• Identify and evaluate emerging technologies for potential open‑source release or commercialization.
• Maintain and optimize cloud and HPC resources for large‑scale data processing.

• Strong software engineering experience (e.g., Python, C++, Rust, or Java) with a track record of building production systems.
• Demonstrated ability to develop and deploy AI/ML models in research settings.
• Experience with multiomics, imaging, or other high‑dimensional biological data is a plus.
• Proficiency in cloud platforms (AWS, GCP, Azure) and HPC environments.
• Excellent problem‑solving skills and a passion for tackling difficult scientific challenges.
• Ability to work independently and take ownership of technical direction.
• Strong communication skills for interdisciplinary collaboration and scientific writing.
• Experience with version control (Git) and CI/CD pipelines.
• Background in quantitative sciences (e.g., computer science, engineering, physics, statistics).
• Evidence of mentorship or leadership in technical projects.