Member of the Technical Staff, Interpretability at Output - ScoutJobs - The AI-curated global job board
Skip to content
O
Posted 6 hours ago

Member of the Technical Staff, Interpretability

OutputMember of the Technical Staff, Interpretability

Perks & benefits

Health InsuranceMedical InsuranceVisa

Requirements

PhD in CS, ML, Physics, or Math with 2+ years experience, Strong publication record (NeurIPS, ICML, ICLR), Proficiency in Python and PyTorch, Experience with large-scale GPU infrastructure, Experience in mechanistic interpretability

Skills

PythonPyTorchMachine Learning

About the role

About the Company

Output is a stealth-mode startup operated by repeat founders and biotech veterans. The company is building biological reasoning models that understand molecular interactions to generate novel therapies, backed by top-tier VCs including Y Combinator.

Responsibilities

  • Develop methods for probing and reverse-engineering model representations to understand biological encoding
  • Design and run experiments to identify and characterize model capabilities regarding molecular interactions
  • Build methods to extract biological understanding as explicit, usable outputs for downstream systems
  • Create tools connecting model internals to meaningful biological concepts for scientists
  • Collaborate with pretraining and generation teams to feed interpretability findings back into model development
  • Own the full pipeline from probing experiments to production-quality interpretability tools on distributed infrastructure

Requirements

  • PhD in CS, ML, Physics, Math, or related field with 2+ years post-doc/industry experience, OR Bachelor's/Master's with 5+ years research/engineering experience
  • Strong publication record at top-tier venues (NeurIPS, ICML, ICLR) in mechanistic interpretability or representation analysis
  • Hands-on experience analyzing internal representations of large neural networks
  • Proficiency in Python and PyTorch
  • Experience working with large models on GPU infrastructure
  • Ability to write production-quality, well-tested, and maintainable code
  • Experience taking research from experiments to usable tools

Preferred Qualifications

  • Background in chemistry, biology, computational biology, or biophysics
  • Experience interpreting ML models trained on scientific or biological data
  • Experience building visualization or analysis tools for model internals
  • Experience with multimodal models
  • Contributions to open-source machine learning projects

Benefits

  • Competitive salary and equity
  • Medical, dental, and vision coverage
  • Feedback-focused environment with high autonomy
ScoutJobs Agent

Get matches like this delivered daily

Sign up free — we'll pull jobs that fit your CV from across the web and rank them for you.

Get started — it's free

Member of the Technical Staff, Interpretability

Output · New York

Sign up to apply