OutcomesAI is a healthcare technology company building an AI-enabled nursing platform designed to augment clinical teams, automate routine workflows, and safely scale nursing capacity.
Our solution combines AI voice agents and licensed nurses to handle patient communication, symptom triage, remote monitoring, and post-acute care — reducing administrative burden and enabling clinicians to focus on direct patient care.
Our core product suite includes:
● Glia Voice Agents – multimodal conversational agents capable of answering patient calls, triaging symptoms using evidence-based protocols (e.g., Schmitt-Thompson), scheduling visits, and delivering education and follow-ups.
● Glia Productivity Agents – AI copilots for nurses that automate charting, scribing, and clinical decision support by integrating directly into EHR systems such as Epic and Athena.
● AI-Enabled Nursing Services – a hybrid care delivery model where AI and licensed nurses work together to deliver virtual triage, remote patient monitoring, and specialty patient support programs (e.g., oncology, dementia, dialysis).
Our AI infrastructure leverages multimodal foundation models — incorporating speech recognition (ASR), natural language understanding, and text-to-speech (TTS) — fine-tuned for healthcare environments to ensure safety, empathy, and clinical accuracy. All models operate within a HIPAA-compliant and SOC 2–certified framework. OutcomesAI partners with leading health systems and virtual care organizations to deploy and validate these capabilities at scale. Our goal is to create the world’s first AI + nurse hybrid workforce, improving access, safety, and efficiency across the continuum of care.
The Role
This sits across backend, platform and AI engineering. Three kinds of work, and you would not do them in equal measure — the balance follows what you are good at and what you want to get better at.
- Backend and data. Multi-tenant services and APIs in TypeScript or python over MongoDB. Clinical content modelling: identity, deduplication, versioning, audit.
- The authoring platform. The tools clinical operations staff use to read and configure triage behaviour — including making genuinely complex logic reviewable by people who are clinicians, not engineers.
- The triage engine. The real-time Python service that runs the calls. Open to you as far as your curiosity takes you
The part people find interesting
A real-time clinical voice agent that cannot be allowed to improvise.
The engine is a hybrid: a deterministic decision graph over clinical content, wrapped in LLM work that has to stay on a leash. Language models handle understanding — extracting facts from what a caller said, classifying answers, screening every turn for life-threatening cues. The clinical decision itself stays deterministic.
The engineering problems that come with that are the good ones: sub-second latency budgets, what to do when a model call times out mid-call, how a safety screen fails open without failing silently, and how you evaluate any of it against recorded sessions rather than vibes.
Most engineers here start on the platform side and move toward the engine as they pick up the domain. That learning curve — clinical triage content, real-time voice, LLM orchestration under safety constraints — is the main reason to take this job over a similar one somewhere else.
You do not need to have built this before. You do need to want to.
What we look for
Strong TypeScript skills with working proficiency in Python. You should be comfortable reading, understanding, and working across the codebase, even when you are not directly modifying every component.
Sound data modelling and schema design judgement. You understand concepts such as identity, versioning, natural keys, stable identifiers, and how data-model decisions affect long-term system behaviour.
A verification-first mindset. When determining how the system behaves, you validate it through the implementation, data, or evidence rather than relying on assumptions. This is especially important in clinical systems, where incorrect conclusions can have significant consequences.
Ability to communicate clearly with non-engineering users. Product labels, explanations, and system behaviour should be understandable to clinicians and operational teams. If the interface can be easily misunderstood, we consider that a product issue rather than a training issue.
Transparency about scope and trade-offs. Priorities change and scope may need to be reduced. We value engineers who clearly communicate what was completed, what was deferred, and any resulting implications.
Technical Stack
TypeScript (Strict Mode)
Node.js & Express
MongoDB
Python
LLM Orchestration
Real-Time Voice Systems
Vite
Vitest
AWS
This Role May Not Be the Right Fit If
You are primarily looking for a greenfield environment. Much of the work involves evolving and strengthening an existing system that users already depend on.
You prioritize feature volume over system correctness. We value getting critical boundaries, interfaces, and behaviours right rather than maximizing the number of features shipped.
You want to focus primarily on model development. This role is more about building the reliable system around AI models—especially how the product behaves when a model is uncertain, inconsistent, or wrong.
