Technical Intern

dmodel
San Francisco
Workplace: OnsiteFull timeUSD 15,000+ monthlyFunction: Healthcare (Clinical, Medical, Wellness)Skills: ["Collaboration","Research ideation","Documentation","Quick iteration","Communication"]

Help build reinforcement learning environments and evaluations used to study how AI agents approach alignment problems. Work with a supervising Member of Technical Staff to run experiments, document model behavior and failure modes, and explore interpretability techniques. Support development of scoped components and test cases, help validate results, and assist with robustness testing against specification gaming while contributing to research discussions across research and engineering.

Loading

Loading job details...

Preparing the role view and application actions.

FursaFursa
dmodel
dmodel
1 day ago

Technical Intern

✓ Verified Job

Canonical indexed version, validated from employer's careers page.

Source: Company careers pageValidated by: Fursa AI
Last checked: 13 minutes agoStatus: Live

Job Summary

Help build reinforcement learning environments and evaluations used to study how AI agents approach alignment problems. Work with a supervising Member of Technical Staff to run experiments, document model behavior and failure modes, and explore interpretability techniques. Support development of scoped components and test cases, help validate results, and assist with robustness testing against specification gaming while contributing to research discussions across research and engineering.
Location: San Francisco
Workplace: Onsite
Employment Type: Full time
Job Function: Healthcare (Clinical, Medical, Wellness)
Seniority: Intern level

Key Responsibilities

  • •Run experiments under guidance and document observed patterns in model behavior and failure modes.
  • •Assist in exploring AI interpretability techniques within the reinforcement learning environments.
  • •Support development of reinforcement learning environments and evaluation suites, including implementing scoped components and writing test cases.
  • •Help test graders for robustness to specification gaming by identifying edge cases and proposing improvements.
  • •Participate in team ideation meetings and research discussions, sharing findings and learning from ongoing research.

Pay and Benefits

Salary: USD 15,000 monthly
Perks:Paid LeaveCommuter BenefitsWellness Stipend

Key Requirements

  • •Strong proficiency in Python and ML frameworks (PyTorch or JAX).
  • •Familiarity with alignment and/or interpretability literature.
  • •Ability to iterate quickly and collaboratively.
  • •Ability to generate research ideas in the field and implement others' ideas.
  • •Prior research experience or experience in AI safety research programs (e.g., MATS, SPAR) is a plus.
Experience:AI safetyReinforcement learningInterpretabilityResearch
Skills:CollaborationResearch ideationDocumentationQuick iterationCommunication
Tech Stack:PythonPyTorchJAX

Eligibility

Work Authorization:Sponsorship available.

Company Brief

dmodel
Builds AI-driven simulation and digital modeling tools to create realistic synthetic environments and datasets for testing, validating, and improving machine learning models and autonomous systems across industries.
Industry: AI & Machine Learning
Website