---
title: 'Staff / Principal Machine Learning Engineer, Serving - UK at Inworld'
canonical: 'https://feeny.ai/job/staff-principal-machine-learning-engineer-serving-uk-inworld-united-kingdom-p52te33gaj10'
type: 'job'
last_seen: '2026-09-06'
---

# Staff / Principal Machine Learning Engineer, Serving - UK at Inworld

- **Company:** Inworld
- **Location:** United Kingdom
- **Employment:** full-time
- **Posted:** 2026-04-07
- **Last confirmed live:** 2026-09-06
- **Apply:** https://jobs.ashbyhq.com/inworld-ai/8a663fc5-3471-49df-8965-9438601ae590

## Job description

## About Inworld

Inworld is a research lab of top researchers and engineers, building the world’s top-ranked realtime voice models.

Today our models are the #1 ranked realtime voice models in the world. They are used to power the largest consumer-facing AI applications available, across categories like health, fitness, learning, therapy, companions, customer experience and media; representing 100s of millions of end users. Our work spans areas like research and development of state-of-the-art models, optimizing realtime inference, and creating best-in-class APIs and products that allow developers to engage their users.

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

The base salary range for this full-time position is £140,000 – £200,000. In addition to base pay, total compensation includes equity and benefits. Within the range, individual pay is determined by work location, level, and additional factors, including competencies, experience, and business needs. The base pay range is subject to change and may be modified in the future.

Candidates must already have the legal right to work in the United Kingdom, as visa sponsorship is not available for this role. For candidates interested in relocating to the San Francisco Bay Area in the future, full U.S. visa and relocation support may be available, subject to business needs and applicable legal and work authorization requirements.

Inworld Jobs Privacy https://inworld.ai/jobs-privacy

## About Inworld

## Company Overview
- **One-liner**: Inworld AI is the realtime AI company that builds voice AI systems—spanning speech-to-text, text-to-speech, and LLM routing—designed to feel as human as it sounds for consumer-facing applications.
- **Entity Type**: Private (Series-stage undisclosed; raised $125M+)
- **Headquarters**: Mountain View, California, USA (with additional presence in Vancouver, Canada)
- **Founded**: 2021
- **Founders**: Kylan Gibbs (Co-founder & CEO), Ilya Gelfenbeyn (Co-founder & CSO), Michael Ermolenko (Co-founder & CTO)

## Core Business
- **Primary industry/industries**: Artificial Intelligence – realtime voice AI infrastructure and research
- **Target customers**: B2B (developers building AI-native applications), B2C (via customer applications such as companions, language learning, interactive media), and Enterprise (Fortune 500 brands like NVIDIA, NBCU, Logitech Streamlabs)
- **Mission or purpose statement**: "To transform static software into living AI systems that autonomously evolve to better serve their users."

## Products & Services
- **Realtime TTS**: Top-ranked realtime text-to-speech on the Artificial Analysis Realtime TTS Arena. Models include `inworld-tts-2` (research preview, 100+ languages with cross-lingual voice identity), `inworld-tts-1.5-max` (GA, 15 languages), and `inworld-tts-1.5-mini` (GA, lower latency). Supports voice cloning from 5–15 seconds of audio. [inworld.ai](https://inworld.ai/)
- **Realtime STT**: Speech-to-text with multi-provider transcription (Inworld, Groq Whisper, AssemblyAI, Soniox) and voice profiling (age, pitch, emotion, vocal style, accent). [inworld.ai](https://inworld.ai/)
- **Realtime API**: Full-duplex voice conversations over a single WebSocket session (STT + LLM + TTS), OpenAI Realtime protocol compatible. Ships in days, fails in fewer places. [inworld.ai](https://inworld.ai/)
- **Realtime Router**: Routes to 220+ LLMs through one OpenAI-compatible endpoint across two tracks: 3P (external providers like OpenAI, Anthropic, Google) and 1P (Realtime Inference). [inworld.ai](https://inworld.ai/)
- **Realtime Inference**: Inworld-hosted, optimized open-source models (Gemma 4, DeepSeek V3.2/V4, MiniMax-M2.5) built for consumer-scale cost and realtime latency. [inworld.ai](https://inworld.ai/)
- **Compute**: Managed GPU for committed high-volume customers requiring predictable latency. [inworld.ai](https://inworld.ai/)

## Market Standing
- **Valuation**: Not publicly disclosed
- **Key Metric**: Total Funding – Over $125M raised
- **Notable Investors/Partners**: Lightspeed Venture Partners, Section 32, Kleiner Perkins, Founders Fund, CRV, Stanford University, Intel Capital, Microsoft M12, Meta, Samsung NEXT, LG Technology Ventures, Bitkraft. Customers include Status by Wishroll, Bible Chat, Talkpal, Particle, Luvu, NVIDIA, NBCU, and Logitech Streamlabs. [inworld.ai/resources/what-is-inworld-ai](https://inworld.ai/resources/what-is-inworld-ai)
- **Growth Signals**: Status by Wishroll reached 1M users in 19 days on Inworld with a 95% AI cost reduction. Bible Chat scaled from 2M to 20M characters/week with an 85% TTS cost reduction. Talkpal serves 5 million language learners using Realtime TTS. [inworld.ai/resources/what-is-inworld-ai](https://inworld.ai/resources/what-is-inworld-ai)

## Competitive Advantages
- **Product-oriented research lab**: The founding team led product for LLMs at DeepMind and built Dialogflow (Google). Maintains a research organization with backgrounds from Google, DeepMind, Meta, Apple, Cruise, Microsoft. [inworld.ai/resources/what-is-inworld-ai](https://inworld.ai/resources/what-is-inworld-ai)
- **Top-ranked realtime TTS**: Ranked #1 on the Artificial Analysis Realtime TTS Arena. [inworld.ai](https://inworld.ai/)
- **OpenAI Realtime API compatibility**: Developers can migrate by swapping the endpoint and auth credentials, lowering switching costs. [inworld.ai/resources/what-is-inworld-ai](https://inworld.ai/resources/what-is-inworld-ai)
- **Full stack of voice infrastructure**: From STT to LLM routing to TTS and managed compute, all in one platform—eliminating the need to stitch together multiple vendors. [inworld.ai](https://inworld.ai/)

## Strategic Focus
- **Realtime AI for consumer-facing applications**: Doubling down on companions, character chat, roleplay, customer support voice agents, sales/SDR agents, phone agents, and language learning. [inworld.ai](https://inworld.ai/)
- **Cost reduction at scale**: Consistently driving down AI costs for customers (e.g., 95% reduction for Wishroll, 85% for Bible Chat) to enable free-tier consumer economics. [inworld.ai/resources/what-is-inworld-ai](https://inworld.ai/resources/what-is-inworld-ai)
- **Enterprise expansion**: Offering on-premise deployment, HIPAA/BAA compliance, EU and India data residency, and dedicated account management. [inworld.ai/resources/what-is-inworld-ai](https://inworld.ai/resources/what-is-inworld-ai)

## Why Work Here
- **Culture**: "A passionate engineering-minded team" where "technical depth is a requirement for deep empathy with our customers." The company states that no matter the role, they only hire technical people. [inworld.ai/careers](https://inworld.ai/careers)
- **Autonomy and impact**: Employees are empowered with autonomy to work across research and engineering, drive product strategy, and "leave their mark on an entire industry." [inworld.ai/careers](https://inworld.ai/careers)
- **Remote/Hybrid/Office**: Not explicitly stated on careers page, but headquarters are in Mountain View, CA, with a presence in Vancouver, Canada. Active job postings are location-specific (e.g., US-based roles). [inworld.ai/careers](https://inworld.ai/careers)
- **Notable perks/engineering culture**: Focus on research and open-source contributions (github.com/inworld-ai). The company describes itself as a "product-oriented research lab" with a strong emphasis on shipping realtime AI products. [inworld.ai/resources/what-is-inworld-ai](https://inworld.ai/resources/what-is-inworld-ai)

## Sources
1. [inworld.ai](https://inworld.ai/)
2. [inworld.ai/careers](https://inworld.ai/careers)
3. [inworld.ai/resources/what-is-inworld-ai](https://inworld.ai/resources/what-is-inworld-ai)
4. [LinkedIn – Inworld AI](https://www.linkedin.com/company/inworld-ai)
5. [Datanyze – Inworld AI Company Profile](https://www.datanyze.com/companies/inworld-ai/559637359)

## Other roles at Inworld

- [Product Marketing Manager - USA](https://feeny.ai/job/product-marketing-manager-usa-inworld-mountain-view-hgkbeava4ea5) — Mountain View, CA
- [Performance Marketing Lead - USA](https://feeny.ai/job/performance-marketing-lead-usa-inworld-mountain-view-srjdwezxy15t) — Mountain View, CA
- [Lead Technical Recruiter - USA](https://feeny.ai/job/lead-technical-recruiter-usa-inworld-mountain-view-ppf2z8f50ns8) — Mountain View, CA
- [Product Lead - USA](https://feeny.ai/job/product-lead-usa-inworld-mountain-view-1w2xc2c0q2sa) — Mountain View, CA
- [Founding AI Solutions Engineer - USA](https://feeny.ai/job/founding-ai-solutions-engineer-usa-inworld-mountain-view-tq1ppzf0qwmq) — Mountain View, CA
- [Staff / Principal Machine Learning Engineer, Serving - Switzerland](https://feeny.ai/job/staff-principal-machine-learning-engineer-serving-switzerland-inworld-f7emse251crp) — Switzerland
- [Senior / Lead Machine Learning Engineer, Serving - Serbia](https://feeny.ai/job/senior-lead-machine-learning-engineer-serving-serbia-inworld-serbia-1vhdr56n8jjb) — Serbia
- [Senior / Lead Machine Learning Engineer, Serving - Germany](https://feeny.ai/job/senior-lead-machine-learning-engineer-serving-germany-inworld-germany-79qa3m65a8m5) — Germany
- [Staff / Principal Machine Learning Engineer, Serving - USA](https://feeny.ai/job/staff-principal-machine-learning-engineer-serving-usa-inworld-mountain-view-sfgvvj07jfhy) — Mountain View, CA
- [Staff / Principal Research Scientist - UK](https://feeny.ai/job/staff-principal-research-scientist-uk-inworld-united-kingdom-vfcekdtr8k1m) — United Kingdom