Bioinformatics Engineer (Spatial & AI Training)

Qualifications

• End-to-end analysis of one or more spatial platforms: Seeker/Trekker (Slide-seq), MERFISH, DBiT-seq, Xenium, Visium, Stereo-seq, GeoMx, CosMx, or similar assays
• 3+ datasets completed from raw data final biological insight for publications or real industry decisions
• Working understanding of kit-specific numerical sanity checks, eg
• QC thresholds, and when results deviate from expectation
• Familiarity with key spatial computational tools (cell segmentation, cell typing, ligand–receptor analysis)
• Strong grasp of experimental design, hypothesis generation, and interpreting spatial-omics papers
• Working knowledge of statistical inference (tests, confidence intervals, estimators)
• Working knowledge of high-dimensional algorithms (PCA, neighborhood graphs, UMAP)

Responsibilities

• Your job is to generate the high-signal training data that powers these agentic biology systems

Full Description

Bioinformatics Engineering Consultant — Spatial & AI Training

(1099 Contract, Onsite SF)(FTE conversion is certainly on the table for top performers)

We're working with a world-class engineering team building biological LLMs that can execute pipelines, interpret results, and reason about data.

These models only become reliable when trained on real expert judgment: workflows, QC thresholds, and failure diagnoses.

Your job is to generate the high-signal training data that powers these agentic biology systems.

You MUST bring hands-on experience with:

• End-to-end analysis of one or more spatial platforms: Seeker/Trekker (Slide-seq), MERFISH, DBiT-seq, Xenium, Visium, Stereo-seq, GeoMx, CosMx, or similar assays.

• 3+ datasets completed from raw data final biological insight for publications or real industry decisions.

• Working understanding of kit-specific numerical sanity checks, eg. QC thresholds, and when results deviate from expectation.

• Familiarity with key spatial computational tools (cell segmentation, cell typing, ligand–receptor analysis).

• Strong grasp of experimental design, hypothesis generation, and interpreting spatial-omics papers.

• Working knowledge of statistical inference (tests, confidence intervals, estimators).

• Working knowledge of high-dimensional algorithms (PCA, neighborhood graphs, UMAP).

Why the Bar Is High

The impact is high.

If this describes your background, we want to work with you.