Skip to content
← Inworld AI

Senior Machine Learning Engineer, Inference - USA

Inworld AI · Mountain View, California, USA

Applied AIonsitesenior$250k–$300k
Apply on the lab’s site ↗

At a glance

Highlights

  • Build realtime AI serving hundreds of millions of users daily.
  • Scale inference to over 10 trillion LLM tokens per month.
  • Power consumer apps across companions, health, education and media.

What they offer

  • Bonus
  • Equity
  • Benefits
  • Relocation assistance

Ideal candidate

Fast-learning builder who thrives in ambiguity and owns unclear problems end-to-end. You obsess over real-world latency, throughput and reliability and ship impact over theory.

Requirements

  • Deep understanding of modern serving frameworks and techniques like vLLM or TRT-LLM
  • Hands-on experience with quantization, distillation, caching strategies, continuous batching, paged attention, and speculative decoding
  • Proficiency in C++, CUDA, Rust, or highly optimized Python with GPU performance profiling
  • Experience with Kubernetes, Ray, custom load balancing, and multi-GPU/multi-node inference at scale
  • Track record of systems programming projects, open-source contributions, or technical deep-dives
  • Ability to take a model from research through containerization, optimization, and reliable production serving
  • PhD in CS, Physics, Math, or equivalent practical experience building backend or ML systems

Lab profile

About Inworld AI

Research lab and inference provider building realtime speech models and LLM APIs for consumer apps.

What they build

  • First-party speech models
  • LLM serving
  • Modular realtime APIs

Known for

  • Realtime AI for consumer-facing applications
  • High-volume realtime inference
  • Infrastructure for large-scale workloads

Key facts

  • Hundreds of millions of users daily
  • Over 10 trillion LLM tokens served per month
More about Inworld AI →
Apply on the lab’s site ↗

Posted · Last seen