Inworld
Inworld builds real-time voice AI and agent infrastructure for developers, including text-to-speech, speech-to-speech, speech recognition, and LLM routing delivered via APIs and SDKs. Customers use it to create interactive characters and agentic experiences in games, apps, and virtual worlds; revenue comes from usage-based and enterprise licensing. Founded in 2021 and headquartered in Mountain View, California, the company is privately held and works with game studios and large technology firms.
Open Positions at Inworld
6 open positions
Build and optimize high-performance machine learning inference systems powering realtime, large-scale AI applications. You’ll take models from research through production, improving latency, throughput, and reliability across NVIDIA GPU infrastructure.
Own the full production lifecycle of realtime multimodal model serving, optimizing inference latency, throughput, and reliability at thousands of queries per second. This remote Switzerland role combines machine-learning systems, GPU performance engineering, and distributed infrastructure ownership.
Own the optimization and production serving of realtime multimodal models at massive scale. You’ll solve hard latency, throughput, and reliability problems across inference engines, GPUs, and distributed systems.
Build and optimize high-performance serving infrastructure for Inworld’s realtime multimodal and agentic models. You’ll own the path from research models to reliable, highly scalable production inference.
Build and optimize production-grade machine learning serving systems for real-time multimodal inference at scale. You’ll own performance, reliability, and distributed deployment across high-performance GPU infrastructure.
Own and scale secure cloud infrastructure and platform tooling for Inworld’s realtime AI products. This high-impact role combines Kubernetes, infrastructure-as-code, CI/CD, reliability engineering, and AI-powered developer workflows.