Senior AI Engineer, Agentic Healthcare Platform – Remote

Medical Virtual Assistants; Dallas (TX); Remote; USD 180,000 - 240,000; Full time

Benefits offered by this job

Health benefits

401(k) plan with match

Tuition Reimbursement

PTO accrual Day 1

Job summary

MedicalVirtual is hiring a senior AI engineer to build and operate a production-grade GenAI platform for patient-facing and enterprise conversational experiences. You will design backend AI services in Python, orchestrate GenAI workflows, and integrate EHR/FHIR-backed experiences with strong security and observability.

The role emphasizes production-grade judgment, API security, tests, and ownership in a small fast-moving team, with benefits and a path to impact in healthcare AI.

Qualifications

• 7+ years of professional software development experience.
• Strong production experience with Python, asynchronous programming, backend APIs, and SOA.
• Hands-on GenAI applications with Google ADK 2.x or similar orchestration.
• Experience with LLM tool calling, multi-agent workflows, RAG, and safe guardrails.
• Experience with LLM providers such as Vertex AI, OpenAI, or Anthropic.
• Proficiency with FastAPI, pytest, Docker, CI/CD, and containerized deployments.
• Security-focused with JWT/OAuth, secrets management, and secure service-to-service comms.
• Ability to design safe healthcare data integration patterns (FHIR/EHR).
• Experience with Azure and/or Google Cloud.
• Strong debugging, testing, and operational problem-solving skills.
• Ability to work in a small, fast-moving engineering team.

Responsibilities

• Design, implement, and maintain backend AI services using Python 3.12+ and FastAPI.
• Develop and operate agentic GenAI workflows with Google ADK 2.x as orchestration.
• Build MCP tool servers and tools for healthcare workflows like care tasks and scheduling.
• Integrate LLM providers and GenAI toolkits (Vertex AI, OpenAI, Anthropic) when needed.
• Implement prompt engineering, RAG, structured output validation, and guardrails.
• Design secure integration boundaries for FHIR, EHR, and patient data.
• Protect PHI and credentials via secure JWT/OAuth, encryption, and audit-safe logging.
• Leverage Azure and Google Cloud services and monitor via observability tooling.
• Write automated tests with pytest, support CI/CD and containerized deployments.
• Collaborate across product, architecture, security, clinical, and DevOps teams.
• Engage in architecture reviews, production support, and incident response.

Skills

Python

Async programming

FastAPI

Google ADK

LLM tool calling

RAG

Guardrails

Security

Observability

Testing

CI/CD

Containerized deployments

JWT/OAuth

PHI protection

Azure/GCP

EHR/FHIR

Docker

LangChain

OpenTelemetry

Education

Tools

Docker

pytest

LangChain

Terraform

Kusto

OpenTelemetry

Job description

Dallas, Texas, Role Summary

We are seeking a senior AI engineer to help build and operate a production-grade healthcare GenAI platform for patient-facing and enterprise conversational experiences. This role will focus on backend AI services, agentic workflows, MCP tool servers, secure clinical data integrations, and AI platform tooling. The ideal candidate is a strong Python/backend engineer with hands-on GenAI experience who can build reliable agent systems using Google ADK , LLM tool calling, structured outputs, RAG, guardrails, and healthcare-safe integration patterns. This is not a prompt-only role; it requires production engineering judgment across security, observability, testing, deployment, PHI protection, and operational ownership.

Primary Responsibilities

• Design, implement, and maintain backend AI services using Python 3.12+ , async service patterns, and frameworks such as FastAPI , Google ADK , and FastMCP .
• Develop and operate agentic GenAI workflows using Google ADK 2.x as a primary orchestration framework.
• Build MCP tool servers and domain-specific tools for healthcare workflows such as care tasks, medications, scheduling, patient profile lookup, clinical record retrieval, and EHR/FHIR-backed experiences.
• Integrate LLM providers and GenAI toolkits including Google Gemini/Vertex AI , OpenAI, Anthropic, and related orchestration frameworks where appropriate.
• Implement prompt engineering, RAG, structured output validation, tool selection patterns, memory strategies, and AI guardrails to support safe and reliable model behavior.
• Design secure clinical integration boundaries for FHIR, EHR, user profile, scheduling, and other healthcare systems.
• Protect PHI and sensitive credentials through secure JWT/OAuth flows, delegated authorization, token forwarding, encryption, redaction, and audit-safe logging.
• Leverage cloud services such as Azure App Configuration, Key Vault, Cosmos DB, Event Hubs, Application Insights , and Google Cloud services such as Vertex AI/Gemini and Cloud Run .
• Build observability, telemetry, evaluation, and impact-reporting capabilities for AI systems and AI-assisted engineering workflows.
• Author and maintain automated tests using pytest and support linting, type-checking, CI/CD, and containerized deployments.
• Collaborate with product, architecture, security, clinical, platform, DevOps, and application teams to deliver safe AI capabilities through well-defined HTTP/MCP contracts.
• Participate in architecture discussions, code reviews, production support, operational readiness, and incident response.

BENEFITS

Our competitive benefits package includes the following –

• Immediate eligibility for health and welfare benefits
• 401(k) savings plan with dollar-for-dollar match up to 5%
• Tuition Reimbursement
• PTO accrual beginning Day 1
• Note: Benefits may vary based upon position type and/or level

Required Qualifications

• 7+ years of professional software development experience.
• Strong production experience with Python , asynchronous programming, backend APIs, and service-oriented architecture.
• Hands-on experience building GenAI applications with Google ADK 2.x or similar agent orchestration frameworks.
• Demonstrated understanding of LLM tool calling, multi-agent workflows, structured outputs, RAG, prompt engineering, and AI safety/guardrail patterns.
• Experience integrating with LLM providers such as Google Gemini/Vertex AI , OpenAI, Anthropic, or equivalent platforms.
• Experience with FastAPI , pytest , Docker, CI/CD workflows, and containerized production deployments.
• Strong understanding of API security, JWT/OAuth , delegated authorization, secrets management, and secure service-to-service communication.
• Ability to design safe integration patterns for healthcare data, clinical systems, or other sensitive regulated environments.
• Experience with cloud-native services in Azure and/or Google Cloud.
• Strong debugging, testing, and operational problem-solving skills.
• Ability to work with high ownership in a small, fast-moving engineering team.
• Strong communication skills and ability to collaborate across engineering, architecture, security, product, and clinical stakeholders.

Preferred Qualifications

• Healthcare domain experience, especially with HIPAA , HL7/FHIR , Epic integrations, patient portals, scheduling, medication, claims, or clinical workflow systems.
• Experience with MCP , FastMCP v3 , model-tool integration, or agent tool-server architecture.
• Experience with LangGraph, LangChain, PydanticAI, Semantic Kernel, or other orchestration and structured-output frameworks.
• Familiarity with OpenTelemetry , Application Insights, Kusto, AI evaluation pipelines, or production observability tooling.
• Experience building AI platform tooling, internal developer enablement tools, AI governance automation, code review automation, or AI impact reporting.
• Experience with uv , ruff, pyright, Python packaging, dependency isolation, and multi-container service deployment.
• Exposure to React and TypeScript for occasional full-stack collaboration, while remaining primarily backend/platform focused.

AI-Augmented Development Expectations

This role requires disciplined use of AI tools as part of daily engineering work. The engineer should be able to use AI coding agents and GenAI systems to accelerate implementation, research, validation, and documentation while remaining fully accountable for correctness and safety. The successful candidate will know how to:

• Give AI agents clear, scoped engineering tasks.
• Require agents to inspect existing code, contracts, tests, and architecture before proposing changes.
• Validate AI-generated code with tests, type checks, linting, runtime review, and security judgment.
• Identify when generated code is unsafe, incorrect, over-engineered, noncompliant, or inconsistent with platform boundaries.
• Use AI tools to improve delivery speed without compromising PHI protection, reliability, auditability, maintainability, or user trust.
• Contribute to AI governance patterns, reusable agent instructions, tool ergonomics, and platform standards.

Ideal Candidate Profile

The ideal candidate is a senior backend/platform engineer with practical GenAI experience and strong healthcare-grade judgment. They can design agent workflows, but they also understand authentication, deployment, observability, testing, failure modes, PHI handling, and operational ownership. They are pragmatic, security-minded, collaborative, and comfortable building early platform foundations that will later support production patient-facing AI experiences.