Senior Data Engineer for AI-Driven Bio Discovery

Mithrl; San Francisco (CA); On-site; USD 180,000 - 220,000; Full time

Benefits offered by this job

Health insurance

401(k)

Job summary

Mithrl in San Francisco seeks a data engineer to own the ingestion and normalization layer for diverse biological data.

You will build robust pipelines, combine classical engineering with LLM-powered cleanup, and collaborate with product, bioinformatics, and infra teams to ensure clean, analysis-ready datasets.

The role offers a mission-driven environment, high ownership, and a chance to impact life sciences through scalable data tooling.

Qualifications

• 5+ years of experience in data engineering / data wrangling with real-world tabular or semi-structured data.
• Strong Python proficiency and data-processing libraries (Pandas, Polars, PyArrow).
• Hands-on experience cleaning messy Excel/CSV data and standardizing it.
• Experience designing robust ETL/ELT pipelines for scientific or lab data.
• Ability to combine traditional data engineering with LLM-powered data normalization.
• Experience owning ingestion and normalization end-to-end with maintainability and scalability.

Responsibilities

• Build and own an AI-powered ingestion pipeline to import data from various sources.
• Develop schema mapping, coercion, and unit normalization during ingestion.
• Structure semi-structured data with metadata extraction and cleaning.
• Ensure core transformations run at ingestion for clean downstream data.
• Build validation and QA layers to catch corrupt data before entry.
• Collaborate with product, data science, and infra to enforce data standards.

Skills

5+ years data engineering

Python

Data wrangling

Tools

Pandas

Polars

PyArrow

Job description

Mithrl in San Francisco seeks a data engineer to own the ingestion and normalization layer for diverse biological data.

You will build robust pipelines, combine classical engineering with LLM-powered cleanup, and collaborate with product, bioinformatics, and infra teams to ensure clean, analysis-ready datasets.

The role offers a mission-driven environment, high ownership, and a chance to impact life sciences through scalable data tooling.