Senior AI/ML Backend Engineer for Scalable GenAI

Aimlroles; Northern (KY); Hybrid; USD 140,000 - 210,000; Full time

Job summary

Lyra Health is seeking a Senior AI/ML Backend Engineer to build the backend services for our AI features. You will own scalable infrastructure and collaborate with therapists, data scientists, engineers and product managers to deliver high-impact solutions.

Responsibilities include Python coding (FastAPI), deploying to Kubernetes, handling streaming data, RAG integration and LLM observability, with AWS cloud experience in a fast-paced healthcare setting.

Qualifications

• 6+ years of experience delivering production ready products.
• Ability to write high-quality code in Python.
• Experience with modern async Python web frameworks (e.g., FastAPI) and handling data streaming (WebSockets, Server-Sent Events).
• Experience working with Docker and deploying applications to Kubernetes.
• Experience with relational and low-latency databases.
• Experience integrating RAG into AI features.
• Experience building generative AI chatbots.
• Experience with LLM observability and monitoring tools (e.g., Langfuse).
• Familiarity with LLM orchestration frameworks (e.g., LangChain, LlamaIndex) and integrating with foundation model APIs (e.g., OpenAI, Anthropic, AWS Bedrock).
• A desire to learn quickly and build systems from scratch.
• Excellent communication and strong prioritization skills.

Responsibilities

• Build ML backend services powering AI product features.
• Create backend infrastructure for scalable, resilient solutions.
• Deploy and manage applications in production.
• Code daily and collaborate cross-functionally with therapists, data scientists, engineers and product managers.

Skills

Python

FastAPI

WebSockets

Docker

Kubernetes

Relational DBs

Low-latency DBs

RAG integration

Generative chatbots

LLM observability

LangChain

LlamaIndex

OpenAI APIs

Anthropic APIs

AWS Bedrock

Tools

Celery

Protobuf

Java/Kotlin

AWS

Job description

Lyra Health is seeking a Senior AI/ML Backend Engineer to build the backend services for our AI features. You will own scalable infrastructure and collaborate with therapists, data scientists, engineers and product managers to deliver high-impact solutions.

Responsibilities include Python coding (FastAPI), deploying to Kubernetes, handling streaming data, RAG integration and LLM observability, with AWS cloud experience in a fast-paced healthcare setting.