RRemoteville

How Remoteville checks and expires listings

In Tandem logoIn Tandem

AI Engineer

Skills
DevopsAI AgentsArtificial IntelligenceDockerKubernetesLanggraphLarge Language Models
Role

What the job involves

The main requirements, responsibilities and hiring steps.

Requirements

  • 5+ years shipping production software including applied AI or ML work
  • Experience running and optimizing self-hosted LLMs on dedicated multi-GPU hardware
  • Hands-on with a serving stack such as vLLM SGLang or TensorRT-LLM
  • Experience with tensor parallelism quantization batching and KV cache optimization
  • Track record of improving inference latency throughput and GPU utilization
  • Strong Python and engineering fundamentals
  • Ability to build quick UI and work across the app layer
  • Hands-on with agent frameworks LLM APIs embeddings and RAG
  • Comfortable with AWS Docker CI/CD monitoring and observability
  • Experience building internal tooling or platforms others depend on

Nice to have

  • Performance-minded
  • Rapid prototyper
  • AI-first builder
  • Collaborative
  • Purpose-driven

Day to day

  • Run and optimize a self-hosted inference stack on dedicated GPU hardware, tuning serving systems for high throughput and low latency.
  • Build the internal AI platform and observability layer that employees rely on, making performance and usage easy to understand.
  • Ship user-facing AI agents and product features that help families coordinate, summarize, draft, schedule, and take action inside the apps.