Key skills
Public Cloud AWSPublic Cloud GCPDistributed SystemsPythonTypeScriptJavaGoFoundation Models OpenAIFoundation Models AnthropicFoundation Models GeminiLLM Integration PatternsRAGAgentic LoopsOrchestration Frameworks LangChainOrchestration Frameworks LlamaIndexMLOpsData PipelinesModel EvaluationModel ObservabilityHIPAA ComplianceGDPR ComplianceHuman-in-the-loop SystemsClinical Decision Support FrameworksModel InterpretabilityAI SafetyEngineering Team LeadershipAIMLGenerative AIGenAILLMOpenAIAnthropicGeminiLangChainLlamaIndexAgenticAWSGCPMentoring
About this role
Rula is a remote-first company dedicated to transforming mental healthcare. As a Principal AI Engineer, you will design and implement AI systems that enhance patient engagement and provider workflows, ensuring technical excellence in a regulated environment.
Responsibilities:
- Own the AI foundation that determines how generative AI shows up across mental healthcare
- Operate where architecture, applied research, and real-world clinical constraints meet
- Design durable, production-grade systems that power patient engagement and provider workflows at scale
- Act as a technical multiplier, architecting core platform primitives (RAG, agentic loops) while setting the standard for technical excellence and safety in a regulated environment
Requirements:
- 10+ years of software engineering experience, including 7+ years with Public Cloud (AWS, GCP, etc.)
- 5+ years designing/scaling distributed systems
- 5+ years of deep experience in Python and at least one other backend language (TypeScript, Java, Go, etc.)
- 2+ years building AI-powered products at scale with foundation models (OpenAI, Anthropic, Gemini, etc.)
- 2+ years of experience with LLM integration patterns such as RAG, agentic loops, and orchestration frameworks like LangChain or LlamaIndex
- 3+ years working with MLOps, data pipelines, evaluation, and observability systems for continuous model improvement
- Experience architecting secure, compliant AI solutions in regulated environments (HIPAA, GDPR)
- Familiarity with human-in-the-loop systems and clinical decision support frameworks
- Experience designing evaluation pipelines for human alignment, factual accuracy, or model interpretability
- Contributions to open-source AI frameworks or applied research in GenAI safety
- Experience leading or mentoring engineering teams in AI or ML platform domains