---
title: 'Senior Data Engineer at Absentia Labs'
canonical: 'https://feeny.ai/job/senior-data-engineer-absentia-labs-san-francisco-64z4yhksra5b'
type: 'job'
last_seen: '2026-11-10'
---

# Senior Data Engineer at Absentia Labs

- **Company:** Absentia Labs
- **Location:** San Francisco, CA
- **Compensation:** $115k–$200k
- **Employment:** full-time
- **Work type:** hybrid
- **Posted:** 2026-11-06
- **Last confirmed live:** 2026-11-10
- **Apply:** https://jobs.ashbyhq.com/absentia-labs/c7937f5e-06ea-4508-b75e-9a8b441d0a33

## Job description

## About Absentia Labs

Absentia Labs is building the data and intelligence infrastructure that powers the next generation of biomedical discovery. We work at the intersection of biology, chemistry, machine learning, and large-scale systems, transforming fragmented scientific data into reliable, machine-learning-ready knowledge.

Biomedical data is dispersed, semi-structured, and inherently noisy, yet deeply interconnected across experiments, assays, compounds, and biological systems. Extracting value from this complexity requires deliberate schema design, principled abstractions, and rigorous post-processing pipelines that can support both scientific reasoning and large-scale AI. We believe breakthroughs start with strong data foundations. This role sits at the architectural core of our platform, shaping how scientific data is modeled, validated, versioned, and served across the organization.

## The Role

As a Senior Data Engineer, you will own the design and evolution of Absentia Labs’ biomedical data platform. You will operate with a high degree of autonomy, making long-horizon architectural decisions while remaining hands-on in implementation. This role is ideal for an engineer who enjoys working in high-ambiguity, research-driven environments, and who understands that data engineering for AI is as much about representation and correctness as it is about scale.

## What You’ll Do

- Architect and lead the design of end-to-end data systems for large-scale biomedical datasets (chemical, biological, toxicology, omics, assay, clinical, and experimental data).
- Define and evolve schema-driven data models that reconcile noisy, semi-structured, and heterogeneous sources into coherent, interoperable representations.
- Establish best practices for data quality, validation, provenance, lineage, and versioning suitable for scientific and ML workflows.
- Build and maintain cloud-native data infrastructure (data lakes, warehouses, object storage, streaming systems) with an emphasis on scalability and reliability.
- Design pipelines that support both batch and streaming access for ML training, evaluation, and inference.
- Partner closely with ML engineers, scientists, and product leads to translate research needs into durable data abstractions.
- Make principled trade-offs around performance, cost, flexibility, and correctness in production systems.
- Provide technical leadership through design reviews, architectural guidance, and mentorship of other engineers.
- Identify and proactively address systemic risks in data integrity, scalability, and operational complexity.

## Who You Are

You are a data engineer who thinks in systems and interfaces, not just pipelines. You are comfortable owning poorly defined problems and converging on robust solutions through thoughtful design and iteration. You understand that biomedical data is rarely “clean,” and that schema design, normalization, and semantics are first-order engineering problems—especially in AI-driven settings.

You Likely Have

- 5+ years of experience in data engineering, platform engineering, or ML infrastructure roles, with clear ownership of production systems.
- Proven experience designing and operating large-scale, production-grade data pipelines.
- Strong proficiency in Python and data-centric software engineering practices.
- Deep experience with cloud platforms (AWS, GCP, or Azure), including storage, compute, and security primitives.
- Familiarity with distributed data processing and orchestration systems (e.g., Spark, Beam, Ray, Airflow, Dagster).
- Experience supporting ML/AI workloads, including dataset generation, feature pipelines, and reproducible training workflows.
- Strong architectural judgment and the ability to communicate technical decisions clearly across disciplines.

Bonus If You Have

- Competitive compensation, including meaningful equity participation, allows you to share directly in the long-term success and growth of the company.
- Prior work with biomedical or life-science data (e.g., omics, assays, molecular representations, clinical or toxicology data).
- Experience with streaming platforms (Kafka, Pub/Sub, Kinesis).
- Exposure to ontology-aware data modeling or schema evolution in scientific domains.
- Infrastructure-as-code and systems experience (Terraform, Docker, Kubernetes).
- Experience in early-stage startups or research-heavy environments.
- Open-source contributions or technical publications.

## What We Offer

- A chance to architect the data backbone of an AI-driven biomedical platform.
- Direct impact on how scientific data is translated into machine intelligence.
- High autonomy, high trust, and ownership over critical systems.
- Flexible remote or hybrid work arrangements.
- A deeply technical, low-ego culture focused on learning and rigor.

How to Apply Please submit your resume and a short note on why this role resonates with you. Links to GitHub, technical writing, or relevant projects are encouraged.

## About Absentia Labs

## Company Overview
- **One-liner**: Absentia Labs builds AI foundation models that predict how medicines behave inside the human body, aiming to replace traditional animal testing with in‑silico whole‑organism models and accelerate drug discovery.
- **Entity Type**: Private (early‑stage startup; backed by Milemark Capital and Kastor Capital)
- **Headquarters**: Boston, MA, USA
- **Founded**: November 2024
- **Founders**: Farhan Khodaee, Rohola Zandie, Robert Betancort

## Core Business
- **Primary industries**: Biotechnology, artificial intelligence for drug discovery, computational toxicology
- **Target customers**: B2B – pharmaceutical companies, biotech firms, and drug development organizations
- **Mission**: “Make human biology increasingly computable, help create safer medicines, reduce reliance on animal testing, and dramatically improve the speed and success rate of therapeutic innovation.”

## Products & Services
- **AI Foundation Models for Drug Behavior**: Large‑scale models that learn from biological, chemical, and clinical data to predict drug safety, efficacy, and behavior in the human body.
- **In‑Silico Whole‑Organism Platform**: Virtual drug testing environment designed to replace early‑stage animal studies with mechanistic, human‑relevant predictions.
- **Digital Liver Model (ISTAND‑qualified)**: An AI‑driven model accepted by the FDA into the ISTAND qualification program to help predict drug‑induced liver injury.
- **Organ‑specific Safety Risk Software**: Toxicological software that identifies organ‑specific risks early, translating preclinical data across species.

## Market Standing
- **Valuation**: Not publicly available
- **Key Metric (Funding)**: Early backing from Milemark Capital and Kastor Capital (amount not disclosed)
- **Notable Investors/Partners**: Milemark Capital, Kastor Capital
- **Growth Signals**:
  - FDA acceptance of Absentia’s AI‑driven digital liver model into the ISTAND qualification program (a major regulatory milestone)
  - Multiple research publications on aging, genotype‑phenotype mapping, and chemical space navigation
  - Active hiring across roles (GTM Engineer, Head of Strategic Partnerships, Head of Translational Science)
  - Spun out of MIT research

## Competitive Advantages
- **Foundation models that generalize across biology** – going beyond narrow dataset predictions to address fundamental biological processes.
- **FDA‑engaged digital liver model** – early regulatory validation for a key safety prediction tool.
- **Multidisciplinary team** merging frontier AI research with deep biological and drug‑development expertise.
- **Focus on replacing animal testing** – addressing ethical, cost, and translational challenges that plague traditional drug development.

## Strategic Focus
- Continue developing and validating AI foundation models for various organ systems.
- Expand the in‑silico platform to cover more safety and efficacy endpoints.
- Engage with regulators (e.g., ISTAND) to drive adoption of computational models in drug approval pipelines.
- Build partnerships with pharma and biotech companies to integrate models into early‑stage R&D.

## Why Work Here
- **Hybrid workspace** – employees work a combination of remote and on‑site in Boston offices.
- **Mission‑driven** – opportunity to make a tangible impact on drug safety and reduce animal testing.
- **Research‑forward culture** – team publishes academic work and attends the cutting edge of AI and biology.
- **Small, agile team** (approximately 7 employees) with close collaboration across disciplines.
- **Roles currently open**: GTM Engineer, Head of Strategic Partnerships, Head of Translational Science.

## Sources
1. [absentia.bio](https://www.absentia.bio/) – Company homepage, founding team, research
2. [builtin.com](https://builtin.com/company/absentia-labs) – Perks, culture, office policy, headcount, open roles
3. [pharmatechnews.com](https://pharmatechnews.com/absentia-labs-drug-discoverys-biggest-bottleneck/) – Launch announcement, investors, MIT spinout details
4. [github.com](https://github.com/absentia-labs) – Public repositories (Graphium, Zaira‑Chem, etc.)
5. [gust.com](https://gust.com/companies/absentia_labs) – Company summary, founding date, location, employee count

## Other roles at Absentia Labs

- [Senior AI/ML Engineer](https://feeny.ai/job/senior-ai-ml-engineer-absentia-labs-boston-spb3d0xaxw7h) — Boston, MA
- [AI Research Scientist](https://feeny.ai/job/ai-research-scientist-absentia-labs-boston-4qfcmxnshets) — Boston, MA
- [Member of the Technical Staff](https://feeny.ai/job/member-of-the-technical-staff-absentia-labs-boston-tjycedpf239r) — Boston, MA
- [Senior Data Engineer](https://feeny.ai/job/senior-data-engineer-smartly-helsinki-9av7334w3d1h) — Helsinki, Finland
- [Senior Data Engineer](https://feeny.ai/job/senior-data-engineer-voicemod-1sx8dtetdybj) — 🇪🇸, Spain
- [Senior Data Engineer](https://feeny.ai/job/senior-data-engineer-partnerize-tel-aviv-w6k7mpb3ft2n) — Tel Aviv, Israel
- [Senior Data Engineer](https://feeny.ai/job/senior-data-engineer-dkb-code-factory-valencia-2bfh5ft4y0jt) — Valencia, Spain
- [Senior Data Engineer](https://feeny.ai/job/senior-data-engineer-coderoad-latin-america-cw3w80d618vx) — Latin America
- [Senior Data Engineer](https://feeny.ai/job/senior-data-engineer-tala-united-states-n1vt1y5jqahm) — United States
- [Senior Data Engineer](https://feeny.ai/job/senior-data-engineer-dfo-referrals-westport-w2ccwz8awrxp) — Westport, CT