Director, AI Alignment and Interpretability (Remote)
USA VA Remote, United States
R
USD 195K-290K Executive-level Full Time
Tasks
- Apply behavioral constraints and deployment guardrails
- Conduct circuit analysis for security capabilities
- Detect offensive misuse signal in model internals
- Develop evaluation framework and benchmarks
- Lead mechanistic explanations of model behavior
- Own alignment and interpretability research agenda
- Perform probing classifiers for vulnerability representations
- Publish original research
- Recruit and develop research scientists
- Run behavioral testing and capability elicitation
- Set priorities for open problems
- Set technical bar through personal contributions
- Translate findings into training interventions
- Use activation analysis for risk surfacing
Perks/Benefits
- Competitive vacation and holidays
- Comprehensive wellness programs
- Employee networks and volunteer opportunities
- Great Place to Work certified
- Paid parental and adoption leaves
- Professional development opportunities
- Vibrant office culture
Skills/Tech-stack
AI alignment | Activation Patching | Adversarial ML | Artificial Intelligence | Behavioral Testing | Capability Elicitation | Causal tracing | Circuit analysis | Feature Visualization | Language Models | Large Language Models | Machine Learning | Mechanistic Interpretability | Offensive security | Probing Classifiers | Vulnerability research
Education
Roles
AI | AI Research Director | Director | Research Director | Research Scientist | Scientist
Related jobs
-
AI Foundry | API Integration | AWS Bedrock | AWS CloudFormation | AWS SageMakerCorporate holidays | Dental insurance | Flexible time off | Home internet allowance | Medical insuranceSenior-level Full TimeRemote R2d ago
-
AI Security Engineer USD 100K-150KAccess Control | Access Management | Adversarial ML | Application Security | AuthorizationSenior-level Full TimeUnited States - Remote R2d ago
-
Data Scientist (Remote) USD 120K-180KAbuse Resistance | Agent safety | Agentic Planning | Data scaling | DeepSpeedEmployee networks | Great Place to Work certified | Office culture | Paid adoption leave | Paid parental leaveMid-level Full TimeUSA VA Remote, United States R2d ago
-
AI Solutions Architect- Federal USD 170K-240KAWS | Adversarial Machine Learning | Agentic AI | Air-gapped | Air-gapped environmentsAnnual workspace upgrades | Flexible time off | Fully remote | Home office stipend | Internet and phone stipendSenior-level Full TimeRemote- US R3d ago
-
AI Security Architect (REMOTE - United States) USD 140K-195KAI Security | Artificial Intelligence | Azure | Azure Data | Azure Data LakeRemote work environmentSenior-level Full TimeFranklin, TN R3d ago
-
AI Security Engineer USD 100K-150KAccess Controls | Access Management | Adversarial Machine Learning | Application Security | AuthorizationSenior-level Full TimeUnited States - Remote R3d ago
-
AI Security Engineer USD 100K-150KAccess Management | Adversarial Machine Learning | Application Security | Cloud Security | CryptographyLong term multi year engagement | Remote work | Visa transfer support for qualified candidatesSenior-level Full TimeUnited States - Remote R3d ago
-
AI Security Engineer USD 100K-150KAccess Management | Adversarial Machine Learning | Application Security | Authorization | Cloud SecurityHealth benefits | Remote work | W2 employmentSenior-level Full TimeUnited States - Remote R3d ago
-
Urgent Hiring: NLP Architect (Security Architect) | Hybrid Role | Local to Texas Preferred USD 124K-188KAI Governance | AI platforms | Agent systems | Cloud AI | Cloud AI Platforms1 week onsite every month | Hybrid workSenior-level Contract Full TimeHouston, TX, United States R4d ago
-
Director, Product Management, Customer Security Outcomes USD 199K-285KArtificial Intelligence | Automation | B2B | Cybersecurity | Generative AIEducation reimbursement | Health plans | Parental leave options | Remote work | Retirement optionsExecutive-level Full TimeRemote - USA R4d ago
-
Director of AI & Machine Learning USD 194K-272KAI Governance | API Integration | Access Control | Audit Logging | Cloud Computing401k plan | Company-Paid Holidays | Corporate discounts | Dental insurance | Health insuranceExecutive-level Full TimeRemote (All), United States R4d ago
-
AI Security Engineer USD 100K-150KAccess Management | Adversarial Machine Learning | Authorization | Cloud Security | CryptographyCareer growth | Equal opportunity employer | Remote workSenior-level Full TimeUnited States - Remote R4d ago
-
AI Security Engineer USD 100K-150KAccess Control | Access Management | Authorization | Cloud Security | CryptographySenior-level Full TimeUnited States - Remote R4d ago
-
Staff Data Scientist USD 195K-265KA/B | A/B Testing | Automl | B testing | Convolutional Neural NetworkSenior-level Full TimeRemote - USA R5d ago
-
AI/ML Engineer II USD 159K-211KAPI Design | AWS | Agent Orchestration | Agent systems | AzureHealth benefits | Onsite collaboration | Paid time off | Professional developmentMid-level Full TimeRemote, USA R5d ago
-
AI/ML Engineer USD 150K-211KAWS | Agent systems | Cloud platform | Data Pipelines | DockerOnsite schedule | WFH FridayEntry-level Full TimeRemote, USA R5d ago
-
AI Security Engineer USD 100K-150KAccess Management | Adversarial Machine Learning | Application Security | Authorization | Cloud SecuritySenior-level Full TimeUnited States - Remote R6d ago
-
AI Security Engineer USD 100K-150KAccess Management | Adversarial Machine Learning | Application Security | Cloud Security | CryptographySenior-level Full TimeUnited States - Remote R6d ago
-
Sr. Director, Analyst, CIO & AI Leader Group – Cybersecurity & Emerging Technologies, Enterprise Risk - Remote, US USD 172K-202KArtificial Intelligence | Blockchain | CCPA | CIS Controls | Cloud SecurityFlexible work environment | Mentoring and coaching | Professional development | Remote work | Travel up to 25 percentSenior-level Full TimeRemote - Texas, United States R6d ago
-
Agent Orchestration | Attention Mechanisms | Guardrails | Language Processing | Machine LearningEmployee networks | Employee volunteer opportunities | Paid adoption leave | Paid parental leave | Paid time offSenior-level Full TimeSunnyvale, United States R6d ago
-
Cyber Data Scientist USD 119K-189KArtificial Intelligence | Data Transformation | Data Visualization | Data virtualization | Database Management SystemsSenior-level Full TimeRemote (United States) R9d ago
-
Senior AI Security Architect USD 117K-161KAI RMF | Artificial Intelligence | Cloud Security | Cloud Security Architecture | Cloud infrastructureSenior-level Full TimeWork at Home - Kentucky, United … R10d ago
-
Staff AI Security Engineer USD 208K-251KAI Security | Access Management | Adversarial Testing | Audit Logging | CI/CD401k match | Child care support | Donation matching | FSA | Fertility care supportSenior-level Full TimeSeattle, WA (hybrid) R10d ago
-
AI Agents | AWS | Agentic AI | CUDA | Deep learningCompetitive vacation and holidays | Comprehensive wellness programs | Employee networks | Great Place to Work certified | Paid adoption leaveSenior-level Full TimeAustin, United States R12d ago
-
Director, AI & Security Development USD 210K-214KAPI Development | Advanced Analytics | Amazon Web Services | Artificial Intelligence | Automation401k | Dental insurance | Disability insurance | Employee stock purchase plan | Enhanced Advocacy ServicesExecutive-level Full TimeRemote - USA, United States R12d ago