About Playbook

Playbook is building the Operating Memory for regulated industries.

In life sciences and other highly regulated sectors, companies run on thousands of written procedures — SOPs, work instructions, policies, manuals, and how-to guides. Employees are expected to find, understand, follow, and stay trained on the right procedure at the right moment. That system is breaking under the weight of information overload.

Playbook turns procedural documents into structured, usable data — making critical operational knowledge consumable by humans, software systems, and AI agents. This living layer of procedural knowledge is what we call Operating Memory.

We work with leading global life sciences companies and are building the foundational data model for procedural knowledge in regulated industries. We're an early-stage, founder-led company with high ambition, high standards, and a strong bias toward execution.

Why now

Enterprise AI agents can't run on fragile data pipelines. They need deterministic, auditable, and low-latency infrastructure under the hood.

The Role

Our platform runs on the Playbook® Operating Memory — an ontology-based knowledge layer that turns company rules, procedures, and regulatory requirements into explicit, machine-executable logic enforced directly in live systems and workflows. Every decision it makes is logged and auditable, with a clear account of why it was allowed, required, or blocked.

We are hiring a Knowledge Graph Engineer to own the production systems behind that translation. You don't need to be an AI researcher — your job is to know when a problem calls for deterministic logic over ML, build the pipelines, APIs, and runtime enforcement that carry that decision into production, and use LLMs only where they add leverage, never as the source of truth.

You will report directly to our CTO and operate as a senior Individual Contributor, collaborating closely with our cross functional teams. Success looks like rules that are explicitly modeled rather than buried in code, a system that's explainable and auditable, and teams that trust it without babysitting it.

What you’ll own

• Build and ship the core knowledge representation layer of the platform (ontology-based, structured, deterministic where required)

• Translate regulatory and operational rules into machine-executable logic

• Design and own: data pipelines, APIs, validation logic, and runtime enforcement mechanisms — and decide when not to use ML (and replace it with formal logic, constraints, or deterministic systems)

• Use LLMs deliberately — for interpretation, assistance, and interface layers; never as an uncontrolled source of truth

• Make and own architectural decisions for the knowledge and enforcement layers (with clear constraints, but real decision authority)

• Own correctness, reliability, and maintainability in production — including defining what “correct” means and how it is verified

What you'll bring

• 5+ years building production systems involving AI, ML, or complex logic

• Strong CS fundamentals (data structures, algorithms, system design)

• Experience in regulated or high-stakes environments (healthcare, pharma, finance, compliance)

• Exposure to: knowledge graphs, ontologies, rules engines, formal logic, symbolic or hybrid AI systems

• Comfort with greenfield systems and long-term ownership

• Willingness to learn novel approaches to knowledge representation (we are building something fundamentally new)

Nice to have

Tech environment (indicative, not dogmatic):

• Python

• Graph databases / ontology tooling

• LLMs with a focus on reliability and control

• AWS

Probably Not a Fit

This role likely isn't for you if you…

• You primarily want to experiment rather than ship

• You optimize for personal comfort, not system impact

• You need heavy process, detailed roadmaps, or constant alignment

• You avoid conflict or direct feedback

• You believe every hard problem should be solved with ML