> Markdown version of [/jobs/ext/4715949-senior-ai-engineer](https://www.wearedevelopers.com/jobs/ext/4715949-senior-ai-engineer). Every page supports `.md` or `Accept: text/markdown`. Links point to the HTML versions so they work for humans too. Agent guide: [/agents.md](https://www.wearedevelopers.com/agents.md). --- # Senior AI Engineer - **Company:** MD ALLY TECHNOLOGIES, INC. - **Location:** United States (Remote available) - **Experience:** Expert - **Contract:** Permanent contract - **Skills:** LangGraph Framework, Application Programming Interfaces (APIs), Artificial Intelligence, Amazon Web Services, Audio Signal Processing, Audit Trail, Automation of Tests, Microsoft Azure, EHealth, Middleware, Monitoring of Systems, Python (Programming Language), Routing, Node.Js, Rapid Prototyping Process, OpenAI, Software Engineering, Data Streaming, TypeScript, Video Editing, Speech Recognition, WebSocket, WebRTC, Pinecone, Fast Healthcare Interoperability Resources, Retrieval-Augmented Generation, Large Language Models, Google Vertex AI, State Machines, Llamaindex, Electronic Medical Records, Generative AI, Backend, Agentic-AI, Pgvector, Health Level Seven International, Build Tools, Data Pipelines - **Published:** November 14, 2026 - **Apply:** https://www.indeed.com/viewjob?jk=74f7cdb06d7993eb ## About the Role * 5+ years of software engineering experience, with 2+ years shipping production LLM, NLP, or speech-to-text applications. * Strong Engineering Fundamentals: High proficiency in Python and TypeScript/Node.js, with deep experience designing reliable APIs, state machines, asynchronous workers, and CI/CD pipelines. * Hands-On Applied AI Stack: Practical experience with LLM orchestration frameworks (such as LangGraph, LlamaIndex, or custom agent harnesses), RAG pipelines, vector databases (such as pgvector or Pinecone), and structured output validation. * Security and Privacy Mindset: Experience building systems under strict compliance frameworks (HIPAA, SOC2) and working with Business Associate Agreements (BAAs) and encrypted data flows. * Cross-Functional Collaboration: Ability to partner directly with clinicians, Product Managers, and Security teams to translate medical protocols into deterministic, testable software. Preferences * Direct experience in digital health, telehealth, or health-tech startups. * Familiarity with healthcare data standards (FHIR, HL7), medical coding (ICD-10, CPT), or EHR integrations (Epic, Athenahealth, Elation). * Experience with real-time audio processing and medical transcription models (such as Whisper, Deepgram Medical, or AWS Transcribe Medical). ## Description MD Ally integrates with public-safety systems so eligible non-emergency 911 callers can reach care from a clinician instead of defaulting to the highest-cost transport and emergency department pathway. That adds a clinical step before a member enters that pathway. We're looking for a Senior AI Engineer to architect, build, and scale our production AI systems. These systems handle PHI and support clinical decisions, so they have to be accurate, private, and auditable. You'll build the infrastructure that makes that true: deterministic guardrails, HIPAA-compliant data pipelines, clinical evaluation suites, and real-time voice and text workflows integrated into our telehealth platform and Electronic Health Records (EHR). What You Will Build and Own Clinician Productivity and EHR Automation Doctors and nurses spend hours clicking through Electronic Health Records. You'll build tools to automate that administrative work: * Ambient Clinical Scribes: Build audio-to-text pipelines using models like Whisper or Deepgram combined with LLMs that listen to telehealth video visits, filter out small talk, and draft structured SOAP notes (Subjective, Objective, Assessment, Plan). * EHR Read/Write Agents: Build integrations using FHIR or HL7 standards that pull a patient's past labs and medications before a visit, and push approved clinical notes, ICD-10 billing codes, or draft prescriptions back into systems like Epic, Athenahealth, or Elation. * Pre-Visit Chart Summarization: Architect Retrieval-Augmented Generation (RAG) systems that digest dozens of pages of messy PDF medical records or specialist referrals into clean, concise summaries with exact source citations for the provider. Patient-Facing Intake and Care Navigation Before or after a virtual visit, patients interact with chat or voice interfaces. You'll build the backend logic that keeps these interactions helpful and safe: * Dynamic Symptom Intake: Build conversational agents that gather a patient's medical history and symptoms before a video call, and ask follow-up questions based on clinical protocols. * Smart Triage and Routing: Develop classification systems that analyze patient messages to route urgent red-flag symptoms (such as chest pain) immediately to an on-call nurse, while routing routine prescription refills or scheduling requests to automated workflows. * Post-Visit Follow-Up and Care Plans: Create automated systems that translate complex medical jargon from a doctor's note into plain-language instructions, medication reminders, and check-ins in the patient's preferred language., * PHI Redaction and Zero-Retention Pipelines: Build middleware that strips names, dates of birth, and SSNs before data reaches external APIs, routing all traffic strictly through HIPAA-compliant endpoints (such as AWS Bedrock, Azure OpenAI, or GCP Vertex AI) under a Business Associate Agreement (BAA). * Deterministic Clinical Guardrails: Implement real-time validation layers that block models from diagnosing conditions, recommending unapproved treatments, or hallucinating drug dosages, forcing standard fallback responses whenever clinical boundaries are crossed. * Real-Time Audio/Video Processing: Engineer low-latency streaming infrastructure using WebSockets and WebRTC so voice agents and live transcription tools respond in milliseconds during live telehealth calls without awkward pauses. Clinical Evaluation and Observability Systems We don't ship a prompt or model change without proving it's safe. You'll build automated testing harnesses: * Synthetic Patient Simulators: Build AI agents programmed to act like patients with specific conditions, accents, or edge-case behaviors to stress-test intake workflows before real patients interact with them. * LLM-as-a-Judge and Clinical Grading Pipelines: Build automated test suites that grade generated SOAP notes against gold-standard physician notes, checking for omitted allergies, incorrect dosages, or hallucinated symptoms. * Audit Logs and Traceability: Maintain full logging systems so that if a clinician or regulator asks why the system suggested an output, our team can trace the exact prompt, retrieved medical document, and model version used.