Principal ML Engineer — Real-Time TTS & High-Performance GPUs

Inworld, Inc.; Mountain View (CA); Presencial; USD 270.000 - 500.000; Jornada completa

Ventajas ofrecidas por este puesto de trabajo

Relocation assistance

Descripción de la vacante

Inworld, Inc. in Mountain View is seeking a Staff / Principal Machine Learning Engineer focused on Inference to design and optimize real-time AI systems.

You will own end-to-end delivery from research to production, containerize models, and push the performance of large-scale serving on NVIDIA GPUs. You should have deep expertise in C++, CUDA, Python or Rust, plus experience with Kubernetes, Ray, and model acceleration techniques.

Formación

• Inference optimization techniques for real-time serving.
• Experience with model acceleration through quantization, distillation, and caching.
• Strong background in high-performance systems on GPUs (CUDA) and optimized Python/C++/Rust.
• Familiarity with distributed systems and scalable serving (Kubernetes, Ray).
• Contributions to open-source projects or notable backend/ML system work.
• Ability to take models from research to production with end-to-end ownership.

Responsabilidades

• Take models from research to containerized production ready services.
• Optimize serving performance and ensure reliability at scale.
• Work with backend and ML infra teams to support real-time inference.
• Contribute to open-source projects or publish technical write-ups.

Conocimientos

Inference optimization

Model acceleration

High-performance systems

Distributed systems

Open-source contributions

Full-cycle ownership

Educación

PhD in CS, Physics, Math, or equivalent

Herramientas

Kubernetes

Ray

vLLM

TRT-LLM

CUDA

Python

C++

Rust

Descripción del empleo

Introducing Inworld Inference, built for consumer AI.

Nearly 8× faster time to first token than most other providers.

Staff / Principal Machine Learning Engineer, Inference - USA

Inworld is a research lab and inference provider focused on realtime AI for consumer-facing applications. We build first-party speech models, serve LLMs, and run the inference behind modular APIs designed for high-volume, realtime workloads.

Hundreds of millions of users interact with Inworld powered apps every day and we serve over 10 trillion LLM tokens per month. Our models and infrastructure support consumer applications across companions, healthcare, fitness, education, media, and more. Our work spans model research, realtime inference, large-scale serving infrastructure, and the APIs developers use to bring these capabilities into production.

We’ve raised more than $125M from Lightspeed Venture Partners, Section 32, Kleiner Perkins, Microsoft’s M12 venture fund, Founders Fund, Meta, Stanford, and others. Our technology has powered experiences from companies including NVIDIA, Microsoft Xbox, Niantic, Logitech Streamlabs, Wishroll, Little Umbrella, and Bible Chat. Inworld has also been recognized by CB Insights as one of the 100 most promising AI companies globally and named one of LinkedIn’s Top 10 Startups in the USA.

Who We're Looking For

A year ago, reliably working agentic systems and sub-second multimodal inference at scale barely existed. Nobody has a decade of experience here. So we're not screening for a resume template — we're looking for strong people from varied backgrounds who learn fast, thrive in ambiguity, and can show us what they've built, broken, and understood.

Experience We Find Useful

You don't need all of this. But you need enough to make a case.

Inference Optimization. Deep understanding of modern serving frameworks and techniques like vLLM or TRT-LLM.

Model Acceleration. Hands-on experience with quantization, distillation, caching strategies , continuous batching, paged attention, and speculative decoding.

High-Performance Systems. Proficiency in C++, CUDA, Rust, or highly optimized Python. You know how to profile code and squeeze every ounce of performance out of NVIDIA GPUs.

Distributed Systems & Scaling. Experience with Kubernetes, Ray, custom load balancing, multi-GPU/multi-node inference, and reliably handling thousands of concurrent connections.

Public work. Non-trivial systems programming projects, open-source contributions to major inference engines, or deep-dive technical write-ups.

Full-cycle ownership. You can take a model from the research team, containerize it, optimize its serving, and ensure it runs reliably in production.

Background. PhD in CS, Physics, Math, or equivalent practical experience building backend or ML systems.

Who Thrives Here

You don’t need a roadmap to start walking; you’re comfortable picking a direction and building the map as you go.

You believe engineering isn't finished until it’s shipped and stable. You have a bias for impact over purely theoretical optimizations.

You don't just ship code; you obsess over the why. You’re the first to question an architecture if you think there’s a better way to solve the core latency or throughput problem.

You aren't satisfied with "the PM said so." You thrive on deep context and want to understand the fundamental logic behind every decision we make.

What Working Here Is Like

We hand you unclear problems and expect you to make them clear. We value engineers who say "I don't know yet" and then design the benchmark or prototype that finds out. We treat performance, latency, and reliability as first-class product features, not a box to check before launch. Impact comes before everything else, though we support sharing work and open-source contributions that move the field forward. Your work should be visible. Flat structure, fast iterations, minimal process theater.

We believe in the power of in‑person collaboration to solve the hardest problems and foster a strong team culture. We offer relocation assistance and look forward to you joining us in our Mountain view office.

The base salary range for this full-time position is $270,000 - $500,000+ bonus + equity + benefits.