Pramaana Labs is a frontier AI lab building the verification layer for AI. Founded in 2025 and headquartered in Palo Alto, we turn complex human knowledge, including tax codes, legal rules, clinical guidelines and security protocols, into a formal representation, so every AI answer can be traced, challenged, and proved. Pramaana's architecture pairs foundation models trained to formalize and reason with a symbolic world model encoded in Lean 4. Pramaana was founded by a team out of Google, DeepMind, and Glean, combining frontier AI researchers and formal methods experts.
The RoleQA/SDET (Software Development Engineer in Test) for a rules-to-proof product. You test every stage of the pipeline, from rule input through formal specs, prover output and proof artifacts to the customer-facing APIs and proof viewers. You raise clear, reproducible defects and verify fixes.
Focus areas: Corner cases and security risks, including exceptions, thresholds, conflicting rules, unsatisfiable inputs, malformed or malicious input, and access and data-handling issues.
Long-term goal: Automate these tests so problems are flagged without manual intervention.
What You'll DoTest the different parts of the product for functionality, from rule input through formal specs, prover output and proof artifacts to the customer-facing APIs and proof viewers. Raise clear, reproducible defects and verify fixes.
Cover corner cases and potential security issues, including exceptions, thresholds, conflicting rules, unsatisfiable inputs, malformed or malicious input, and access and data-handling risks.
As time goes on, work on automating these tests so that these are flagged without manual intervention.
3+ years in QA, SDET or ML/LLM evaluation, hands-on test automation experience (Python preferred)
Experience testing non-deterministic or data-heavy systems (LLMs, ML pipelines, rules engines).
Automation and CI/CD experience (pytest or similar, GitHub Actions or Jenkins).
Logical rigor: edge cases, constraints, counterexamples.
Ability to turn dense rule-based text into precise test cases, and to write clear bug reports.
LLM eval and benchmark design.
Tax, law or compliance background.
Property-based testing and API testing.
Skills Required
- 3+ years of experience in QA, SDET, or ML/LLM evaluation
- Hands-on test automation experience
- Experience testing non-deterministic or data-heavy systems, such as LLMs, ML pipelines, or rules engines
- Automation and CI/CD experience
- Logical rigor with edge cases, constraints, and counterexamples
- Ability to convert dense rule-based text into precise test cases
- Ability to write clear bug reports
- Python experience
- LLM evaluation and benchmark design
- Tax, law, or compliance background
- Property-based testing experience
- API testing experience
What We Do
Pramaana Labs builds the verification layer for AI, translating complex human knowledge—including tax codes, clinical guidelines, legal rules, and safety constraints—into machine-checkable logic. Its domain-specific systems use provers and solvers to search solution spaces and return proof artifacts, counterexamples, and traceable explanations for expert review. The aim is to make AI answers verifiable, challengeable, and defensible, supporting more accountable AI deployment across high-stakes applications.
