Python Developer (AI focus)

SolveMD is working on a mission-critical project for a US customer to refactor an existing Proof of Concept (AgentVoice) into a robust series of microservices that transcribe doctor-patient encounters, transform transcriptions into structured clinical notes, and generate actionable insights to reduce administrative burden on physicians.

• Senior-level proficiency in Python 3.11+ with focus on asynchronous programming (asyncio) and high-performance API development.
• Extensive experience with FastAPI or Flask for scalable microservices.
• Deep knowledge of LangChain or LlamaIndex for managing LLM chains, memory, and retrieval.
• Experience with Pydantic for data validation and SQLAlchemy/Tortoise-ORM for database interactions.
• Familiarity with Kafka and Redis/Valkey for asynchronous transcription tasks and background jobs.
• Advanced React 18+ (Hooks, Context API, Suspense) and TypeScript skills.
• Experience with Zustand, TanStack Query (React Query), or Redux Toolkit for state management.
• Proficiency in Tailwind CSS and component libraries (e.g., Shadcn/UI) for clinical dashboards.
• Experience with WebSockets or Server-Sent Events (SSE) for live transcription updates.
• Hands-on experience with Claude 3.5/4 (Anthropic) and OpenAI models.
• Ability to implement and extend MCP servers connecting LLMs with secure medical databases and external tools.
• Experience building Custom Skills and Plugins for AI agents.
• Advanced prompt engineering skills including system prompting, few-shot learning, and JSON mode/function calling.
• Comfort working in multi-cloud environments (AWS or GCP).
• Mastery of Docker and Kubernetes (K8s) for deploying and scaling microservices.
• Nice to have: Experience with GitLab CI for automated testing and deployment.
• Nice to have: Knowledge of Prometheus or Grafana for monitoring AI system performance.
• Ability to work significant daily overlap with US Eastern Time zone, including late afternoon and evening hours in Poland.

Service Evolution:

• Architect and refactor the AgentVoice POC into a scalable, resilient microservices architecture.

Agentic Frameworks:

• Design and implement Custom Skills and Plugins that enable LLMs to execute deterministic code and medical actions.

MCP Integration:

• Build and extend Model Context Protocol (MCP) servers to securely bridge LLMs with clinical databases and external healthcare tools.

Prompt Engineering:

• Develop and fine-tune complex system prompts using few-shot learning and JSON-mode output to ensure rigorous medical accuracy.

Backend:

• Build high-performance, asynchronous APIs using Python 3.11+ and FastAPI/Flask to process real-time medical data.

Frontend:

• Create responsive clinical dashboards using React 18 and TypeScript, allowing doctors to review and edit AI-generated insights.

Real-time Systems:

• Implement WebSockets or SSE for live, low-latency transcription streaming during patient encounters.

Data Integrity:

• Use Pydantic for strict validation and manage database interactions via SQLAlchemy or Tortoise-ORM.

Transcription Orchestration:

• Manage pipelines converting passive audio into text and then into structured clinical notes via LangChain/LlamaIndex.

Cloud & DevOps:

• Deploy and scale services across GCP and AWS using Docker and Kubernetes (K8s).

Reliability:

• Monitor AI performance and reliability using Prometheus or Grafana.

Rapid Prototyping:

• Continuously validate and integrate bleeding-edge AI libraries.

This role requires significant daily overlap with the US Eastern Time zone (typically a -6 hour difference from Poland) and availability during late afternoon and evening hours in Poland to facilitate real-time collaboration with the US engineering team.