Principal Machine Learning Engineer, Inference

πŸ•’ October 14

Where this job comes from

Posted on Inworld AI's careers page β†—Inworld AI's careers page, not through a job board

First seen by Remote Rocketship October 14

Still open on Inworld AI's site. Checked 1 hour ago.

Apply Now
Logo of Inworld AI

Inworld AI

51 - 200 employees

Founded 2021

πŸ’Ό Consulting

πŸ€– Artificial Intelligence

πŸ”Œ API

πŸ’° $50M Series A on 2022-08

Consulting β€’ Artificial Intelligence β€’ API

Inworld AI is a developer-focused conversational AI platform that provides a realtime, provider-agnostic runtime and high-quality TTS for building expressive voice agents and virtual characters. It offers multilingual, low-latency streaming voice, instant cloning, emotion and non-verbal controls, and an API-based integration layer with templates and pipelines optimized for scale and cost. The platform is used across games, media, contact centers, and other interactive experiences to boost engagement and reduce infrastructure costs.

πŸ“‹ Description

β€’ Build first-party speech models and serve LLMs for realtime, consumer-facing applications β€’ Develop and operate inference behind modular APIs for high-volume, realtime workloads β€’ Optimize model serving for latency, throughput, and performance at scale β€’ Containerize models and transition them from research into reliable production systems β€’ Work with inference frameworks, distributed systems, Kubernetes, Ray, load balancing, and multi-GPU/multi-node infrastructure β€’ Design benchmarks or prototypes to clarify ambiguous technical problems β€’ Profile and optimize code running on NVIDIA GPUs β€’ Contribute to systems programming, open-source inference engines, or technical write-ups β€’ Collaborate with research and engineering teams to ship stable, high-impact systems

🎯 Requirements

β€’ Deep understanding of modern serving frameworks and techniques such as vLLM or TRT-LLM β€’ Hands-on experience with quantization, distillation, caching strategies, continuous batching, paged attention, and speculative decoding β€’ Proficiency in C++, CUDA, Rust, or highly optimized Python β€’ Ability to profile code and optimize NVIDIA GPU performance β€’ Experience with Kubernetes, Ray, custom load balancing, multi-GPU/multi-node inference, and handling thousands of concurrent connections β€’ Non-trivial systems programming projects, open-source contributions to major inference engines, or deep-dive technical write-ups β€’ Ability to take a model from research through production deployment and reliability β€’ PhD in CS, Physics, or Math, or equivalent practical experience building backend or ML systems β€’ Must already have the legal right to work in the United Kingdom β€’ Visa sponsorship is not available for this role

πŸ–οΈ Benefits

β€’ Equity β€’ Benefits β€’ Potential future U.S. visa and relocation support for relocation to the San Francisco Bay Area, subject to business needs and applicable legal and work authorization requirements

Apply Now

πŸ“Š Check your resume score for this job

Improve your chances of getting an interview by checking your resume score before you apply.

Similar Jobs

πŸ•’ September 30

Depop

201 - 500

πŸ›οΈ eCommerce

πŸ‘— Fashion

🌍 Social Impact

Senior Machine Learning Scientist building pricing and shipping models for Depop’s peer-to-peer circular fashion marketplace. Leading production ML, experimentation, and optimisation initiatives.

πŸ•’ September 24

Primer

51 - 200

πŸ’³ Fintech

Senior ML Engineer building production ML features and smart payment routing. Shaping Primer’s machine-learning foundations for its global payments infrastructure.

πŸ•’ August 28

Iambic Therapeutics

51 - 200

πŸ₯ Healthcare

πŸ’Ό Consulting

🏭 Manufacturing

Machine Learning Scientist post-training Enchant’s multimodal foundation models. Advancing Iambic Therapeutics’ AI-driven drug discovery and medicines development platform.

πŸ•’ August 11

Ravelin Technology

51 - 200

☁️ SaaS

πŸ’³ Fintech

πŸ” Security

Senior Machine Learning Engineer building scalable, multi-GPU fraud-detection systems for Ravelin, a machine-learning fraud detection company. Leading ML infrastructure, data pipelines, MLOps, and model deployment reliability.

πŸ•’ June 22

Prima

1001 - 5000

πŸ’Ό Consulting

πŸ“¦ Logistics

πŸ›‘οΈ Insurance

Software Engineer specializing in Machine Learning for motor insurance solutions at Prima. Responsible for developing and implementing analytical models to enhance claims management processes.

Built byΒ Lior Neu-ner. I'd love to hear your feedback β€” Get in touch via DM or support@remoterocketship.com
Follow Remote Rocketship on LinkedInFollow Remote Rocketship on InstagramFollow Remote Rocketship on FacebookFollow Remote Rocketship on TikTok