Senior AI/ML Backend Engineer

Role overview

Join Lyra Health as a Senior AI/ML Backend Engineer to build and operate backend services that power the company’s AI/ML product features. You’ll take ownership of your work, lead cross-functional initiatives, and deliver scalable, high-performance infrastructure.

Responsibilities

• Design and implement backend services for AI/ML product functionality.
• Build backend infrastructure for scalable, resilient, high-performance solutions.
• Deploy and manage production applications, ensuring high code quality.
• Work on production systems handling streaming and operational needs.
• Lead cross-functional projects that support AI/ML capabilities end to end.

Requirements

• 4+ years building and delivering production-ready products.
• Strong backend engineering with Python, producing high-quality code.
• Experience building generative AI chatbots.
• Familiarity with LLM observability/monitoring tools (e.g., Langfuse) to track latency, token usage, and output quality.
• Experience with LLM orchestration frameworks: LangChain and/or LlamaIndex.
• Ability to integrate with foundation model APIs: OpenAI, Anthropic, and AWS Bedrock.
• Experience implementing RAG (Retrieval-Augmented Generation).
• Proficiency with modern async Python web frameworks (e.g., FastAPI) and data streaming via WebSockets and Server-Sent Events.
• Experience with relational and low-latency databases.
• Hands-on with Docker and Kubernetes deployment.
• Experience with Celery.
• Experience setting up and maintaining vector databases.
• Ability to define and use Protobuf messages.

Nice-to-haves / Additional signals

• Experience writing production code in Java/Kotlin.
• Experience working with highly sensitive data in a healthcare environment.
• Cloud experience, especially AWS.
• A strong systems mindset (building from scratch) and willingness to learn quickly.
• Ability to balance quality and deadlines in a fast-paced environment.