"Computational Postdoctoral Fellow (Plant Genomic Language Models-gLMs)"

Berkeley Lab's LBNL Joint Genome Institute JGI has an opening for a Computational Postdoctoral Fellow to contribute to the development, benchmarking, and application of plant genomic language models (gLMs) to advance biological discovery.

In this exciting role, you will design benchmarking tasks across diverse plant species, optimize model architectures to account for the complexity of plant genomes, and systematically compare language models to traditional deep learning methods. You will apply these models to uncover novel biological insights, particularly in cross-species and data-limited scenarios, and will be expected to communicate findings through high-impact publications and presentations.

This position has an anticipated start date of October 1, 2025.

What You Will Do:

• Develop a comprehensive benchmark suite to evaluate plant genomic language models (gLMs), incorporating tasks across diverse taxonomic groups to assess cross-species transfer learning capabilities.
• Systematically compare gLM-based approaches (including fine-tuned and task-adapted models) with supervised deep learning methods using standardized benchmarks.
• Train and evaluate a range of model architectures and training strategies tailored to the complexity of plant genomes, optimizing for factors such as genome size, repetitive content, and evolutionary distance.
• Identify biological applications where gLMs offer significant advantages, particularly in data-limited tasks or those requiring cross-species generalization.
• Leverage gLM predictions to uncover novel biological insights into plant genome function, including the discovery of previously uncharacterized regulatory elements and evolutionary patterns across species.
• Contribute to manuscript preparation and present research findings at scientific conferences.
• Maintain detailed documentation of code, analyses, and experimental results to ensure reproducibility and transparency.

What is Required:

• A recent Ph.D. (within the last 1-3 years) in Computational Biology, Bioinformatics, Computer Science, Genomics, or a related field.
• Experience with genomic language models, including model training, fine-tuning and application to biological datasets.
• Demonstrated proficiency in Python with the ability to develop, maintain, and document scientific software.
• Experience with biological sequence analysis tools and bioinformatics workflows.
• Experience with high-performance computing (HPC) environments and managing large-scale genomic datasets.
• A strong foundation in genomics, including genome structure, gene regulation, and functional genomic elements.
• Excellent oral and written communication skills including the ability to present complex computational concepts to varying audiences and a strong publication record in peer-reviewed journals in the fields of computational biology, genomics, or machine learning.
• Demonstrated interpersonal skills including experience collaborating within an interdisciplinary research team.

Desired Qualifications:

• Expertise in genome annotation, including experience with standard annotation pipelines and commonly used file formats.
• Experience working with plant genomics data and associated biological challenges.
• Hands-on experience with deep learning frameworks such as PyTorch or TensorFlow including the ability to implement and customize neural network architectures.
• Proficiency in handling genomic data formats (e.g., FASTA, FASTQ, SAM/BAM, BED, GFF/GTF, VCF) and processing high-throughput sequencing datasets.
• Background in regulatory genomics or gene expression prediction, with an understanding of transcriptional regulation and associated computational methods.

Notes:

• Application Deadline: For full consideration, please apply with a curriculum vitae (CV) or resume and cover letter describing your interest in this position by September 2, 2025.
• Appointment Type: This is a full time, exempt from overtime pay (monthly paid), 2 year (benefits eligible), Postdoctoral Fellow appointment with the possibility of renewal based upon satisfactory job performance, continuing availability of funds, and ongoing operational needs. You must have less than 3 years of paid postdoctoral experience.
• Salary Information: The monthly salary range for this position is $7,987 - $8,921 and is expected to start at $7,987 or above. This position is represented by a union for collective bargaining purposes. Postdoctoral Fellow positions are paid on a step schedule per union contract and salaries are predetermined based on postdoctoral step rates. Each step represents one full year of completed post-Ph.D. postdoctoral and/or related research experience.
• Background Check: This position may be subject to a background check. Any convictions will be evaluated to determine if they directly relate to the responsibilities and requirements of the position. Having a conviction history will not automatically disqualify an applicant from being considered for employment.
• Work Modality: Work will be performed onsite at Lawrence Berkeley National Lab located at 1 Cyclotron Road, Berkeley, CA 94720. Work schedules are dependent on business needs. A REAL ID or other acceptable form of identification is required to access Berkeley Lab sites (for more information click here).