Computational Biologist (Genomics & Variant Interpretation)

Lifecode; New York (NY); On-site; USD 140,000 - 200,000; Full time

Job summary

Lifecode, a direct-to-consumer whole genome sequencing company, seeks its first dedicated genomics data hire to transform raw WGS into trusted wellness insights. This build-from-scratch role will define pipelines, interpretation logic, evidence standards, and models trained on our data.

You will own the end-to-end process from raw data to consumer-facing insights, driving practical, scalable genome interpretation for the masses.

Qualifications

• PhD or MS in computational biology or related field.
• Hands-on with human genetic data and VCF wrangling.
• Proficient in Python and SQL for data analysis.
• Knowledge of statistical genetics and PRS/GWAS interpretation.
• Ability to assess literature and translate into product insights.

Responsibilities

• Design and own secondary/tertiary analysis pipeline: alignment, variant calling, QC, annotation.
• Build the variant interpretation layer from ClinVar, gnomAD, GWAS Catalog, etc.
• Develop and validate polygenic risk scores and trait-prediction models.
• Evaluate and deploy modern variant effect predictors.
• Collaborate with product/engineering to ship insights to customers.

Skills

Python

SQL

Genetic data analysis

VCF wrangling

Variant effect prediction

Literature interpretation

Education

PhD or MS in computational biology / bioinformatics / human genetics

Job description

Lifecode is a direct-to-consumer whole genome sequencing company. We sequence your entire genome and turn it into personal wellness insights you can actually use. We're a small founding team and we're building the data and interpretation engine that makes 3 billion base pairs meaningful to a regular person.

The role

You'll be our first dedicated genomics data hire and own how we go from raw WGS output to interpreted, trustworthy insights. This is a build-from-scratch role: the pipelines, the variant interpretation logic, the evidence standards, and the models we train on our data will largely be your call.

What you'll do

• Design and own our secondary/tertiary analysis pipeline: alignment, variant calling, QC, annotation
• Build the variant interpretation layer — curating evidence from ClinVar, gnomAD, GWAS Catalog, PharmGKB and similar sources into wellness and trait insights
• Develop and validate polygenic risk scores and trait-prediction models
• Evaluate and deploy modern variant effect predictors
• Work with our product/engineering lead to ship insights into the customer-facing product

What we're looking for

• PhD or MS in computational biology, bioinformatics, human genetics, or a closely related field
• Hands-on experience with human genetic data (VCF wrangling, Python interpretation libraries) and inference with SOTA in-silico variant effect prediction models (AlphaGenome, Enformer, SpliceAI, etc.)
• Strong Python and SQL;
• Working knowledge of statistical genetics — PRS construction, GWAS interpretation, population stratification
• Ability to read a paper, judge the evidence, and decide whether it belongs in a consumer product
• Bias toward shipping. You've worked somewhere small or you want to.
• Founders' previous companies have driven over $30M+ in revenue and 5B+ views on social media
• This is not a traditional, slow-moving life-sciences company, we will taking frontier research and quickly delivering it to the masses