Carenodes ยท 4 hours ago
AI/ML Engineer Intern
Carenodes is seeking a founding ML engineer to scale and optimize their LLM systems in development through production. This hands-on role focuses on latency, cost, and reliability in real-world healthcare workloads while collaborating cross-functionally to evolve their system.
Responsibilities
Collaborating with the offshore engineering team and executive leadership
Designing and improving routing logic across multiple LLMs (quality vs latency vs cost)
Fine-tuning or adapting models used within the graph
Improving system-level performance (latency, throughput, load-balancing)
Evaluating trade-offs between different LLMs for healthcare-specific tasks
Building guardrails and evaluation loops to ensure reliability and consistency
Supporting the transition from prototype workflows to scalable production systems
Qualification
Required
Experience building LLM systems that route across multiple models
Familiarity with orchestration frameworks (LangGraph, LangChain, or similar)
Designing and iterating on prompts as part of end-to-end LLM workflows
Ability to collaborate effectively with backend and product engineers
Comfort operating in early-stage systems that are evolving quickly
Preferred
Experience designing LLM routing strategies (fallbacks, confidence-based routing, cost-aware decisions)
Prior work on LLM evaluation frameworks or automated QA
Healthcare or regulated-domain experience
Experience scaling AI systems from low to moderate/high traffic