
Staff AI Engineer (Orchestration)
Heidi
Melbourne
16 Mar 2026
Staff AI Engineer (Orchestration)
Staff AI Engineer (Orchestration) role at Heidi, an AI Care Partner company in healthcare. Requires Staff-level experience in search, NLP, or LLM systems, with expertise in Python, SQL, modern IR/NLP, and MLOps. Responsibilities include designing retrieval and question-answering stacks, leading cross-functional teams, and productionizing services.
Hybrid
Full-time
Principal
Python
SQL
Salary
Not specified
Core Qualifications
Technical (Must-have)
PythonSQLembeddingsANN indexesre-rankersretrieval-augmented generationprompt synthesisprogram synthesisPyTorchdistributed training
Soft Skills
leadershipcross-functional collaborationdecision-makingcoachingclear thinkingsafety focusprivacysecurity
Tools (Must-have)
Kubernetesfeature registriesmodel registriesexperiment trackingmonitoringalerting
Preferred Qualifications
Technical (Nice-to-have)
SNOMED CTUMLSICDRxNormFHIRBM25ANNlearned re-rankersLLM inferencecachingbatching
Key Responsibilities
- Define the end-to-end architecture for literature and guideline ingestion, normalization, metadata extraction, de-duplication, and versioning.
- Build hybrid search and retrieval: lexical + vector + re-ranking, with tight latency budgets and cost controls.
- Design grounding and answer synthesis that cite sources, preserve provenance, and expose confidence and abstention.
- Lead model work across prompting, fine-tuning, distillation, and tool use to improve faithfulness, coverage, and utility.
- Stand up gold-standard evaluation: offline IR metrics (nDCG, MAP, recall), factuality/faithfulness audits, and human review with adjudication.
- Run online experiments at scale. Define guardrails, KPIs, and ship A/Bs to measure impact on clinician workflows.
- Productionize services with observability, tracing, canaries, rollbacks, and incident playbooks.
- Set data governance for medical content: access control, PHI handling, audit logs, and retention policies.
- Partner with clinicians to define intents, schemas, and acceptance criteria. Convert ambiguous questions into testable specs.
- Coach engineers and scientists. Raise the technical bar through design docs, reviews, and reusable components.
AI EngineerOrchestrationHealthcareSoftware DevelopmentEngineeringInformation TechnologyFull-timeHybridSearchNLPLLM