Senior Staff Software Engineer (AI Team)

About Us

splose is the AI-powered practice management platform powering better health care. Trusted by over 25,000+ Allied Health professionals around the world, splose is purpose-built to free clinicians from admin and let them focus on what matters most - helping people. Backed by leading VC funds EVP, Spectrum Equity, and Athletic Ventures we have recently announced a record-breaking $46M Series A raise - the largest Series A of any South Australian SaaS company ever. We’re growing fast and investing in our product, our people, and our global growth.

About You

You're a senior engineer who has built production AI systems, not just experimented with them, and you understand the gap between a slick demo and something clinicians can trust every day. You think in terms of architectural boundaries, deterministic tests around non-deterministic behaviour, and observability that catches problems before users do.

In this role, you'll help build and evolve the AI features that are changing how clinicians work: voice transcription, intelligent note generation, semantic search, and in-product AI experiences. The AI Scribe team owns the full stack, from audio capture and voice-processing pipelines through LLM integration and vector-search infrastructure to the product surfaces practitioners use in every clinical session. You'll also help define the security and reliability controls, including threat models and SLIs/SLOs, that keep this premium service dependable at scale. AI Scribe runs at sustained load across a platform serving over 28,000 practitioners, so reliability and data integrity aren't optional extras, they're core to the company's growth targets.

What you'll do

Build and maintain AI features end to end, including voice and audio pipelines, LLM integrations, embedding and vector search infrastructure, and the clinical facing AI surfaces built on top of themSolve AI specific reliability and quality problems such as context window management, rate limiting, streaming failures and model upgrades, with solutions that stay transparent and trustworthy to the practitionerTreat security as part of standard AI delivery: scope every AI query to the organisation, prevent prompt injection, handle audio and file data securely, and stay ahead of model and dependency vulnerabilitiesDesign and ship in-product systems that drive AI adoption, including onboarding experiences, usage nudges and experiments that help clinicians form habits with AI featuresEstablish comprehensive observability and data lineage tracking for AI workflows, and define and monitor SLIs/SLOs (token usage, latency, error rates) to catch degradation before it reaches cliniciansAct as the technical standard bearer for the squad by enforcing rigorous code reviews, defining paved paths for architecture, and establishing engineering practices that prioritise reliability and maintainabilityDrive continuous improvement in squad delivery metrics, particularly Lead Time for Changes, by shipping voice pipelines and LLM integrations with deterministic automated tests that validate system boundaries before deploymentMeet or exceed defined SLOs and error budgets for all AI components, and reduce Mean Time to Recovery for AI specific incidents through robust observability and actionable runbooksDefine and enforce clear architectural paved paths that reduce the cognitive load required for other engineers to safely interact with non-deterministic AI componentsMaintain a zero-incident record on cross-tenant data bleed by mitigating prompt injection risks and data isolation vulnerabilities at the architectural design phase, not after releasePartner with the Principal Security Engineer on threat models and controls, and with the Head of Engineering Enablement on resilience models and controls

What you'll bring

Expert level application of architectural boundaries and structural design patterns (Ports and Adapters, Inversion of Control, SOLID) to keep AI integrations decoupled, verifiable and strictly validatedAdvanced testing capability, including dependency injection, mocking, contract testing and deterministic test harnesses for non-deterministic AI behaviour, with experience implementing shift-left testing to validate LLM boundaries and data contracts early in CI/CDProduction experience integrating LLMs, including the OpenAI API (chat completions, embeddings, streaming, function calling), context window management, token counting, and a strict emphasis on validating and sanitising LLM generated function arguments before backend executionStrong TypeScript across Node.js backend and React frontend, with deep expertise in the Node.js/V8 runtime including async I/O, event loop mechanics and memory profiling to prevent thread blocking in high throughput pipelinesExperience building async and event-driven pipelines, including message queues (SQS or equivalent), background workers, and retry and fallback handlingUnderstanding of vector databases and semantic search, including embedding models, indexing, chunking strategies and retrieval qualitySolid understanding of multi-tenancy, treating organisation-level data isolation on every AI query as a hard requirement, not a guidelineExperience with AI observability, including tracing, error rate monitoring and token usage analyticsHands-on AWS experience across S3, SQS, Lambda, DynamoDB and SSMMastery of modern Node/React testing frameworks (Jest, Vitest, Playwright) and paradigms such as TDD, contract testing and black box testingAbility to scope and deliver independently while surfacing complexity and risk earlyClear communicator who can explain AI capabilities, limitations and failure modes to both clinical and non-technical stakeholders

Good To Have

Familiarity with AWS Bedrock or an equivalent managed LLM serviceHealthcare or other regulated-industry domain experienceExperience with LLM observability tools such as Langfuse, including trace grouping, token usage tracking and prompt versioningExperience with AI evaluation methods such as LLM-as-a-judge, output quality assessment and regression detection across model upgradesExperience with experimentation platforms such as PostHog for feature flags, A/B testing and adoption analyticsExperience with browser recording APIs, presigned URLs and voice pipeline architectureA relevant university degree or equivalent practical experience

Next Steps

Only shortlisted candidates will be contacted for an initial screening call by our internal TA team.

Equal Opportunity Employer

splose is an equal opportunity employer. We celebrate diversity and are committed to creating an inclusive environment for all employees. If you need support and adjustments in participating in this process, please let us know!

We are not accepting recruitment agency submissions for this role.