---
title: "Research Scientist, Biological Sequence Foundation Models"
slug: "research-scientist-biological-sequence-foundation"
id: "3540a3dd-3b36-43bd-a649-a0c3da26d0c6"
department: "AI Research"
department_code: "RES"
location: "Zurich, Switzerland"
workplace_type: "Hybrid"
employment_type: "Full-time"
compensation: "CHF 150k – CHF 200k (annual package)"
is_remote: false
is_featured: false
headcount: 1
canonical_url: "https://jobs.talent247.co/jobs/research-scientist-biological-sequence-foundation"
markdown_url: "https://jobs.talent247.co/jobs/research-scientist-biological-sequence-foundation.md"
apply_endpoint: "https://jobs.talent247.co/api/public/jobs/research-scientist-biological-sequence-foundation/apply"
schema_endpoint: "https://jobs.talent247.co/api/public/jobs/research-scientist-biological-sequence-foundation/form-schema"
webmcp_tool: "apply_for_role"
updated_at: "2026-11-15T17:22:44.075Z"
content_signal: "search=yes, ai-input=yes, ai-train=no"
---

# Research Scientist, Biological Sequence Foundation Models

## Position Telemetry

- **Reference:** `RESEARCH-SCIENTIST`
- **Practice / Sector:** AI Research (`RES`)
- **Location:** Zurich, Switzerland
- **Workplace Type:** Hybrid
- **Employment Type:** Full-time
- **Compensation:** CHF 150k – CHF 200k (annual package)
- **Canonical HTML URL:** https://jobs.talent247.co/jobs/research-scientist-biological-sequence-foundation

## Role Dossier & Specification

THE CLIENT & MANDATE
Our client is a premier European generative AI-for-biology company operating tightly integrated dry-lab ML research and automated wet-lab facilities across Zurich and Amsterdam. Backed by top trans-Atlantic venture funds, they build foundation models for protein programming that allow pharmaceutical and industrial-biotech partners to simultaneously optimize binding affinity, thermostability, expression yield, and immunogenicity across far fewer experimental wet-lab rounds.

They have partnered with Talent247 to appoint a Research Scientist, Biological Sequence Foundation Models at their Zurich research center. Working closely with computational biologists, ML engineers, and wet-lab protein scientists, you will design and pre-train next-generation evolutionary, structural, and assay-conditioned foundation models that learn the underlying grammar of functional biomolecules.

KEY RESPONSIBILITIES
• Formulate, pre-train, and scale novel autoregressive, masked-diffusion, and flow-matching foundation models over billions of evolutionary protein/nucleotide sequences, 3D structural tokens, and biophysical assay readouts.
• Develop sample-efficient post-training,test-time guidance, and Bayesian/RL active-learning methods that adapt foundation representations to sparse, noisy multi-parameter wet-lab experimental data.
• Design calibrated uncertainty-estimation and out-of-distribution generalization frameworks so wet-lab synthesis budgets focus on high-probability, diverse functional variants.
• Collaborate directly with internal wet-lab biologists to design prospective experimental validation campaigns that rigorously test new modeling hypotheses in physical assays within weeks.
• Scale clean, modular JAX or PyTorch pre-training code across multi-node H100 clusters, optimizing tokenization, data mixtures, and long-context sequence attention.
• Publish impactful methodological advances at leading ML and computational biology venues and mentor fellow researchers.

TECHNICAL ENVIRONMENT & OFFERING
Their research platform runs on PyTorch/JAX, multi-node GPU clusters, custom biological sequence/structure data lakes, and automated high-throughput wet-lab pipelines. Based hybrid in central Zurich, our client offers CHF 150,000–CHF 200,000 base salary plus meaningful equity, Swiss pension and social benefits, and full Swiss work-permit/relocation assistance.

## Core Requirements

ESSENTIAL QUALIFICATIONS
• PhD in Machine Learning, Computational Biology, Bioinformatics, Biophysics, or a related quantitative discipline (or equivalent frontier research experience).
• Strong publication track record at premier venues such as NeurIPS, ICML, ICLR, RECOMB, ISMB, Nature Methods, or Nature Machine Intelligence.
• Deep hands-on expertise pre-training or post-training large transformer, state-space, or discrete diffusion foundation models in PyTorch or JAX.
• Solid understanding of protein language models, 3D structural representations, multiple-sequence alignments (MSAs), or active learning in experimental design.
• Ability to bridge mathematical modeling rigor with clean distributed engineering and cross-disciplinary communication with wet-lab scientists.

PREFERRED / BONUS EXPERIENCE
• Direct experience validating ML-generated antibodies, enzymes, or peptides in closed-loop wet-lab design-build-test-learn cycles.
• Experience with multi-objective optimization, GFlowNets, reinforcement learning for molecular design, or custom CUDA/Triton attention kernels.

## Application Schema & Direct Apply (`apply_for_role`)

Candidates and authorized AI agents on behalf of a candidate can submit an application via the declarative WebMCP form tool `apply_for_role` on https://jobs.talent247.co/jobs/research-scientist-biological-sequence-foundation or via HTTP `POST https://jobs.talent247.co/api/public/jobs/research-scientist-biological-sequence-foundation/apply` (`application/json` or `multipart/form-data`). Non-browser HTTP agents must include header `X-Talent247-Intake-Token` obtained from `GET https://jobs.talent247.co/api/public/intake-token` (or automatically returned in `GET https://jobs.talent247.co/api/public/jobs/research-scientist-biological-sequence-foundation/form-schema`).

### Form Fields

- `full_name` (text, required): Full name
- `email` (email, required): Email
- `phone` (phone, optional): Phone
- `location` (text, optional): Location
- `linkedin_url` (url, optional): LinkedIn URL
- `cover_letter` (textarea, optional): Cover letter
- `consent` (checkbox, required): I consent to my data being processed for this application
- `cv_file` / `cv_base64` + `cv_filename`: Upload a CV in .pdf or .docx format (<= 10 MB) or provide an `https://` LinkedIn profile URL in `linkedin_url`.

### Alternative: Talent Pool Intake (`join_talent_pool`)

If this mandate is not an exact match, register once in the Talent247 Talent Pool at https://jobs.talent247.co/talent-pool (`https://jobs.talent247.co/talent-pool.md`) via WebMCP tool `join_talent_pool` or `POST https://jobs.talent247.co/api/public/talent-pool`.
