Senior AI Engineer – Databricks / GenAI (Healthcare)
- Location
- Johannesburg, Gauteng
- Contract
- Permanent
- Closing date
First listed . Last checked at source .
In brief
Overview Blue Pearl is recruiting for a Senior AI Engineer to develop a Generative AI (GenAI) reporting solution. This role is for a leading private hospital group. The solution will utilize Large Language Models (LLMs) to transform patient and clinical data stored in Databricks into accurate, clinician-ready reports. The successful candidate will be responsible for translating clinical reporting requirements, designing LLM-powered workflows, implementing retrieval-augmented generation (RAG), establishing evaluation and safety controls, and deploying the solution into production. What you will do * Translate clinical reporting requirements into the required data points and build governed tables in Databricks. * Design prompts, templates and orchestration workflows to generate structured narrative reports. * Build retrieval capabilities over clinical guidelines and policy documents where required. * Implement guardrails to ensure generated statements are grounded in source data and sensitive patient information remains protected. * Develop LLM evaluation frameworks with clinical stakeholders, including test datasets, automated scoring and regression testing. * Deploy the solution into production with monitoring, audit trails and cost controls. * Demonstrate progress to clinical stakeholders during each sprint and incorporate feedback into ongoing improvements. Requirements (from the original advert) Essential Technical Requirements: * Experience in AI/ML engineering, including at least one LLM solution delivered into production. * Strong Databricks experience, including: * Unity Catalog * Delta Lake * Databricks Workflows * MLflow * Mosaic AI Model Serving * Vector Search * Production-standard Python, PySpark and SQL skills. * Prompt engineering and orchestration experience using LangChain, LangGraph, DSPy or equivalent frameworks. * Experience generating structured outputs from LLMs. * Hands-on experience designing, tuning and evaluating retrieval-augmented generation (RAG) solutions. * Knowledge of LLM evaluation methods, including golden datasets, groundedness scoring, LLM-as-judge and regression testing. * Experience implementing guardrails, hallucination controls and sensitive personal data protection. Preferred / Advantageous Requirements: * Healthcare data experience, including admissions, clinical coding (ICD-10), case management or funder interactions. * Working knowledge of POPIA and South African health data governance. * Azure experience, including Azure OpenAI, Key Vault and private networking. * Databricks Generative AI Engineer or Machine Learning Professional certification. Who should apply This role is suitable for a Senior AI Engineer with proven experience in AI/ML engineering, specifically having delivered at least one LLM solution into production. The ideal candidate will possess strong Databricks expertise across components like Unity Catalog, Delta Lake, MLflow, Mosaic AI Model Serving, and Vector Search. Proficiency in Python, PySpark, and SQL is essential, along with experience in prompt engineering, orchestration frameworks (e.g., LangChain), and designing/evaluating RAG solutions. Knowledge of LLM evaluation methods and data protection practices is also required. Candidates with healthcare data experience, familiarity with POPIA and South African health data governance, or Azure experience are at an advantage. The role requires comfort with a hybrid work arrangement from Waterfall City. Deadline Not specified Reference Original posting: https://www.jobmail.co.za/jobs/it-computer/other-it-computer/johannesburg/senior-ai-engineer-%E2%80%93-databricks-genai-healthcare-id-7606054 Source: jobmail
Summary drafted with AI assistance from the original advert. The advert itself is the authority — how we use AI.
At a glance
- Python
- SQL
- Azure
Extracted automatically from the advert; confirm requirements on the original listing.
Job description
Before you apply
- Confirm the requirements and closing date on the original listing (jobmail). SPANi lists vacancies from other sites and may not reflect last-minute changes.
- Legitimate employers do not charge application, registration or training fees.
- Don't send your ID or bank details before you have confirmed the employer is real.
Applying for permanent roles
- Mirror the job title and top three requirements in your CV summary and most recent experience.
- Quantify results where possible: sales targets, cases handled, tickets closed, or team size.
- Proofread contact details and filenames before submitting — small errors cost interviews.
- Verify the company and role on the source page before sharing ID copies or banking details.