Senior Applied AI Engineer(AI Lead)

Key responsibilities

• Architecture: design a shared AI platform layer for all four products: model access, prompt and version management, retrieval, tool calling, logging and cost tracking.
• Model selection: choose and benchmark LLM, speech-to-text and text-to-speech providers on accuracy, latency, cost and data residency in the UAE and KSA.
• Evaluation: build automated test suites (evals) with golden datasets, so that every prompt or model change is measured before release. Track hallucination, omission and accuracy rates.
• Safety and compliance: put guardrails, redaction of patient data, audit trails and human-in-the-loop review in place, in line with HIPAA, DHA, Saudi PDPL and our SOC 2 and ISO 27001 controls.
• Hands-on delivery: write production code in Python and TypeScript for the hardest parts: agent logic, real-time voice and speech pipelines, and EMR integration.
• Team leadership: break work into tasks for our developers, review AI-related pull requests, and coach the team on building with LLMs and AI coding tools.
• Infrastructure: work with DevOps on deployment, monitoring of AI behaviour, rollback and cost controls on Azure.
• Clinical partnership: work with the clinical specialist to turn medical requirements into test cases and rules for the agents.
• Customer-facing support: join technical conversations with hospital clients and regulators on how our AI works and how it is validated.Must-have qualifications
• 6+ years of professional software engineering, including ownership of systems in production.
• 2+ years building LLM-powered features that real users rely on in production. Demos and course projects don't count.
• Strong Python. Working knowledge of TypeScript and Node.js.
• Hands-on with agent design: tool and function calling, structured outputs, multi-step workflows, and handling failures and retries.
• Has built retrieval-augmented generation (RAG): chunking, embeddings, vector search (pgvector, Qdrant, Azure AI Search or similar) and checking retrieval quality.
• Has designed and run evaluation pipelines (LLM-as-judge, golden sets, regression tests), and can show how they measured output quality.
• Experience with at least one major LLM API (Anthropic, OpenAI, Azure OpenAI or Google) and its tradeoffs on cost, latency and context.
• Solid grounding in security and privacy for sensitive data: PII/PHI handling, access control and audit logging.
• Clear written and spoken English. Able to explain AI behaviour to hospital IT teams and non-technical executives.Nice to have
• Real-time voice agents: LiveKit, Pipecat, Vapi, Retell, Twilio or SIP, and tuning latency below 1 second.
• Speech recognition and diarization (Whisper, Deepgram, Azure Speech, AssemblyAI), especially for Arabic or medical vocabulary.
• Healthcare data standards: FHIR, HL7 v2, ICD-10, CPT and SNOMED CT.
• Has shipped an ambient scribe, clinical documentation or medical coding product.
• Azure (AKS, Azure OpenAI, AI Search) and observability tools for LLMs (Langfuse, LangSmith, Arize or similar).
• MCP (Model Context Protocol) servers, or agent frameworks such as the Claude Agent SDK, LangGraph or similar.
• Experience leading or mentoring a small engineering team.
• Familiar with GCC healthcare regulation (DHA, DoH Abu Dhabi, Saudi MOH, NPHIES).