Forward Deployed Engineer

Description

Company

Pramaana Labs is a frontier AI lab building the verification layer for AI. We turn complex human knowledge, including tax codes, legal rules, clinical guidelines and security protocols, into formal representations that support reasoning people can inspect and check. Our architecture pairs models trained to formalize and reason with a symbolic world model encoded in Lean 4. Founded in 2025 and headquartered in Palo Alto, Pramaana brings together researchers and formal methods experts from Google, DeepMind, and Glean.

Responsibilities

• The hardest questions in AI emerge when systems meet messy reality. Can ambiguous, exception-filled rules be formalized faithfully? Can we distinguish what is proved from what is assumed, and make the results reliable enough to use? As a Forward Deployed Engineer, you'll work where applied research, software engineering and customer problems meet. Alongside Pramaana engineers and researchers, you'll prototype and evaluate verifiable AI workflows, build tools and integrations, and help take promising systems into production. You'll investigate failures and turn lessons from the field into improvements to our research, models and core technology. We're looking for engineers who think from first principles, learn fast and care deeply about making AI reasoning verifiable. You don't need years of enterprise deployment experience. You'll have strong technical guidance while owning your work and handling real customer challenges with maturity.
• Understand the real technical problem. Work with customers and domain experts to turn source material, rules, exceptions and constraints into clear requirements and success criteria.
• Prototype verifiable AI workflows. Experiment with model-based formalization, symbolic reasoning and proof checking on challenging real-world inputs. Find out what works and where it breaks.
• Build rigorous evaluations. Create representative examples, edge cases and benchmarks to measure rule fidelity, correctness, coverage and robustness. Reproduce failures and investigate them carefully.
• Take systems into production. Build and debug applications, APIs, tools and integrations. Iterate with customer teams, explain limitations and help deliver reliable workflows.
• Close the loop with research. Work with researchers to turn customer issues and evaluation results into better representations, models, proof workflows and core technology.
• Own problems and improve what comes next. Ask sharp questions, take responsibility for scoped work, communicate blockers early and turn one-off fixes into reusable patterns where possible.
• Strong software engineering fundamentals. You can write clean code, reason about data structures and algorithms, and debug unfamiliar problems.
• First-principles and logical thinking. You question assumptions, isolate the essential problem and explain your reasoning clearly.
• High initiative and a habit of learning quickly. You have examples of making meaningful progress without waiting for detailed instructions.
• A genuine interest in Pramaana's mission. You are deeply excited about reliable, verifiable AI to study the problem and build in this space.
• Clear written and verbal communication, including the maturity to stay calm, be candid about uncertainty and work constructively with customers.
• Comfort learning from more experienced engineers, asking for help when needed and incorporating feedback quickly.
• Especially Strong Candidates May Also Have
• Built an impressive personal project, research prototype, hackathon project or meaningful open-source contribution from scratch.
• Experience with Python or TypeScript, APIs, backend development, LLM applications, evaluation or developer tools.
• Explored formal verification, theorem proving, Lean, logic, symbolic reasoning or AI reliability through work or self-directed learning.
• Hands-on experience working with users, handling unexpected problems or explaining technical ideas to non-specialists.