Inworld AI

Research Scientist

• Conduct research on realtime AI for consumer-facing applications
• Develop and improve foundation models, speech models, LLMs, and related AI architectures
• Design and run experiments to clarify ambiguous research questions
• Build evaluation benchmarks, evaluation loops, and quality measurement systems
• Investigate multimodal models, agents, tool use, test-time compute, and world models
• Take research from question framing through experimentation, publication, and production deployment
• Ship research results for high-impact consumer applications
• Collaborate daily with US-based leadership and engineering teams
• Share impactful work that advances the field when appropriate

Explore Senior Research Scientist at Inworld AI. Review requirements and application details.

Senior Research Scientist

• Conduct research on foundation models, evaluation, and frontier AI topics
• Train models and develop new architectures, reinforcement learning, reward modeling, and scaling approaches
• Design benchmarks, evaluation loops, quality measurements, LLM-as-judge systems, and failure analyses
• Research multimodal models, agents, tool use, test-time compute, and world models
• Frame research questions and design experiments to investigate them
• Write research papers and publish findings
• Ship research results into production
• Build and demonstrate public AI projects, interdisciplinary experiments, or open-source contributions
• Work on first-party speech models, LLM serving, realtime inference, large-scale serving infrastructure, and modular APIs for high-volume realtime workloads

Explore Staff/Principal Research Scientist at Inworld AI. Review requirements and application details.

Staff/Principal Research Scientist

Machine Learning Engineer

• Build and optimize realtime inference systems for consumer-facing AI applications
• Work with first-party speech models, LLM serving, and modular high-volume realtime APIs
• Optimize model serving and inference performance using modern serving frameworks and acceleration techniques
• Profile and optimize code and NVIDIA GPU workloads for latency and throughput
• Scale inference across Kubernetes, Ray, multi-GPU, and multi-node environments
• Handle thousands of concurrent connections reliably
• Take models from research through containerization, serving optimization, and production deployment
• Collaborate daily with US-based leadership and engineering teams
• Design benchmarks or prototypes to resolve unclear performance and reliability problems
• Contribute to impactful engineering work and, where appropriate, open-source projects and technical write-ups

Explore Senior / Lead Machine Learning Engineer, Inference at Inworld AI. Review requirements and application details.

Senior / Lead Machine Learning Engineer, Inference

• Conduct research on realtime AI for consumer-facing applications
• Work on first-party speech models, LLM serving, realtime inference, large-scale serving infrastructure, and modular APIs
• Frame unclear research questions and design experiments to answer them
• Train and develop foundation models and advanced AI architectures
• Build evaluation benchmarks, evaluation loops, and quality measurement systems
• Research multimodal models, agents, tool use, test-time compute, and world models
• Take full-stack ownership from research question through experiments, publications, and shipped results
• Collaborate in person with the team in the Mountain View office
• Contribute to AI capabilities supporting companions, healthcare, fitness, education, media, and other consumer applications

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

Explore Principal Machine Learning Engineer, Inference at Inworld AI. Review requirements and application details.

Principal Machine Learning Engineer, Inference

• Optimize inference using modern serving frameworks and techniques
• Accelerate models through quantization, distillation, caching, continuous batching, paged attention, and speculative decoding
• Profile and optimize high-performance code for NVIDIA GPUs
• Build and scale distributed inference systems using Kubernetes, Ray, custom load balancing, and multi-GPU/multi-node infrastructure
• Handle thousands of concurrent connections reliably
• Take models from the research team through containerization, serving optimization, and production deployment
• Design benchmarks or prototypes to clarify ambiguous technical problems
• Challenge architectures to improve latency and throughput
• Ensure engineering work is shipped and stable
• Collaborate daily with US-based leadership and engineering teams
• Contribute to public technical work and open-source projects where appropriate

Explore Senior Machine Learning Engineer, Inference at Inworld AI. Review requirements and application details.