Genomic ML Engineer - Plant DNA Language Models (Remote UK)

Society; United Kingdom; Remote; GBP 30,000 - 40,000; Full time

Job summary

IsoGentiX is a young UK company building a genomic language model to identify plants and their medicine-like genes from DNA, with research funded by UK grants. We adapt state-of-the-art language models to plant genomes and benchmark performance across noisy long-read data.

We offer a three-month full-time contract, with remote work within the UK and a target decision by January 2027. The project emphasizes responsible benefit-sharing and capacity building in genomic science.

Qualifications

• Hands-on experience training DL models on DNA/RNA/protein sequences.
• Experience with contrastive or metric learning and benchmark design.
• Proficient with PyTorch on cloud GPUs.
• MSc or PhD in ML, computational biology or bioinformatics, or equivalent.
• Right to work in the UK.

Responsibilities

• Adapt an open plant DNA language model to noisy Oxford Nanopore reads.
• Train two heads for species identification and alkaloid pathway gene detection.
• Run benchmarks on held-out genomes comparing current tools.
• Document results for a technical white paper.

Skills

Deep learning on sequences

Contrastive learning

Benchmark design

Education

MSc/PhD in ML / computational biology

Tools

PyTorch

Job description

IsoGentiX is a young UK company building a genomic language model to identify plants and their medicine-like genes from DNA, with research funded by UK grants. We adapt state-of-the-art language models to plant genomes and benchmark performance across noisy long-read data.

We offer a three-month full-time contract, with remote work within the UK and a target decision by January 2027. The project emphasizes responsible benefit-sharing and capacity building in genomic science.