Full Stack AI Engineer
Core
Build AI applications for healthcare workflows, including RAG systems, agentic workflows, and real-time voice agents.
Role type
Full Stack AI Engineer
Builds
RAG pipelines, agentic workflows, real-time voice agents, backend services, and REST APIs
Domain
Healthcare + Generative AI
Deliverable
production ML models | product features
Required skills
RAG system design, LLM API integration, Python, JavaScript/Node.js, LangChain, LangGraph, real-time voice application development, message queue management
Preferred skills
Docker, CI/CD tools, Jira, HIPAA compliance, MongoDB, AWS services, multi-agent coordination, prompt engineering, LLM evaluation
Technologies
Azure AI Foundry, Amazon Bedrock, OpenAI, LangChain, LangGraph, Retell, BullMQ, RabbitMQ, Amazon SQS, Docker, AWS (ECS, Lambda, ALB), Parse, MongoDB
Responsibilities
Design and build RAG pipelines; Integrate LLM provider APIs; Develop agentic workflows; Build real-time voice agents; Develop application features and backend services; Design REST APIs and asynchronous processing workflows; Implement structured outputs and fallback behavior; Establish tracing, evaluation, and monitoring
Seniority
Mid-to-Senior, hands-on IC