AI Researcher
As an AI Researcher at Octave-X, you will work at the frontier of safe and verifiable AI. Your primary focus will be developing new methods at the intersection of formal verification, AI safety, and model interpretability — areas that are central to Tenzin’s mathematical guarantees and Octave-X’s mission. This is a deeply technical role that combines theoretical rigor with practical impact: you will design and run experiments, publish peer-reviewed research, and collaborate with engineering teams to bring your ideas from paper to production. You will operate with significant autonomy to explore novel research directions while staying connected to the real-world constraints and opportunities of enterprise deployment. You will shape the long-term technical vision for how Octave-X builds AI systems that are provably safe, interpretable, and aligned with human intent.
Role Snapshot
Team
Research
Location
Hybrid — Chicago, IL
Compensation
$120,000 + benefits
What You Will Build
Advance the state of the art in formal verification, AI alignment, and trustworthy AI methods — and translate breakthrough research into production-grade systems at Octave-X.
- Develop novel approaches to verifiable, controllable, and interpretable AI behavior grounded in formal methods and type-theoretic foundations.
- Design and execute rigorous experiments across safety, alignment, robustness, and model quality benchmarks with reproducible methodology.
- Publish research findings at top-tier venues (NeurIPS, ICML, ICLR, CAV, POPL) and present work to both internal and external audiences.
- Collaborate with ML engineering and infrastructure teams to prototype, validate, and productionize research outputs into Tenzin and the Octave-X platform.
- Contribute to the long-term research roadmap and technical direction for safe AI at Octave-X, identifying high-leverage problems and novel research trajectories.
- Mentor junior researchers and contribute to building a world-class research culture grounded in intellectual honesty and scientific rigor.
Required Qualifications
- PhD or equivalent research track record in machine learning, formal methods, programming languages, or a closely adjacent field.
- Strong publication history at top-tier ML or PL/verification conferences, or demonstrated applied research impact in industry.
- Excellent mathematical foundations — comfort with proof-based reasoning, type theory, category theory, or related formal frameworks.
- Proficiency building research prototypes in Python with modern ML stacks (PyTorch, JAX) and rapid experimentation workflows.
- Ability to fluidly move between theoretical investigation and product-oriented constraints, balancing rigor with practical impact.
- Strong written and verbal communication skills — you can explain complex ideas clearly to both researchers and engineers.
Nice To Have
- Research experience in type theory, theorem proving, program synthesis, or Homotopy Type Theory specifically.
- Hands-on experience with AI alignment, red-teaming, adversarial robustness, or constitutional AI methods.
- Track record of transitioning research prototypes into shipped, production-grade systems used by real customers.
- Familiarity with proof assistants (Lean, Coq, Agda, Isabelle) or formally verified software development practices.
Apply For AI Researcher
Submit your application with resume attachment. We review every submission.