Senior 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

The AI team builds the features that are changing how clinicians work: voice transcription, intelligent note generation, semantic search, and in-product AI experiences. The 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 join a focused AI squad of engineers, a product manager, and a designer, led by a hands-on engineering manager who contributes directly to the AI backend. You own delivery end to end, from cloud infrastructure and async processing pipelines through backend services and APIs to React UI. At our scale, AI reliability and data integrity are not optional; they are load-bearing requirements at every layer of the stack, and you treat them that way by default.

You've shipped LLM-powered features in production and know where they break: context limits, rate limits, streaming failures, model upgrades. You scope every AI query to the organisation as a hard requirement, not an afterthought. You instrument what you build so problems surface before they affect practitioners, and you communicate clearly with non-technical stakeholders about what AI can and can't do.

What you'll do

Build and maintain AI features end to end: voice and audio pipelines, LLM integrations, embedding and vector search infrastructure, and the clinical-facing AI surfaces built on top of them

Solve AI-specific reliability and quality problems, including context window management, rate limiting, streaming failures, and model upgrades, with solutions that are transparent and trustworthy to the practitioner

Treat 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 vulnerabilities

Design and ship in-product systems that drive AI adoption, including onboarding experiences, usage nudges, and experiments that help clinicians form habits with AI features

Instrument and monitor AI quality, including token usage, trace grouping, and error rates, so problems are caught before they affect practitioners

Participate in code review and informally support less experienced engineers through pairing and feedback

What you'll bring

Required

Production experience integrating LLMs, including OpenAI API (chat completions, embeddings, streaming, function calling), context window management, and token counting

Strong TypeScript across Node.js backend and React frontend in a team environment

Experience building async and event-driven pipelines: message queues (SQS or equivalent), background workers, retry and fallback handling

Understanding of vector databases and semantic search: embedding models, indexing, chunking strategies, retrieval quality

Solid understanding of multi-tenancy: every AI query scoped to an organisation, data isolation treated as a hard requirement

Experience with AI observability: tracing, error rate monitoring, token usage analytics

Hands-on AWS experience across S3, SQS, Lambda, DynamoDB, and SSM

Relevant university degree or equivalent practical experience

Nice to have

Familiarity with AWS Bedrock or equivalent managed LLM services

Healthcare or regulated-industry domain experience

Experience with LLM observability tooling such as Langfuse, including trace grouping, token usage tracking, and prompt versioning

Experience with LLM-as-a-judge patterns, output quality assessment, or regression detection across model upgrades

Experience with PostHog or equivalent for feature flags, A/B testing, and adoption analytics

Experience with browser recording APIs, presigned URLs, or voice pipeline architecture

Next Steps:

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