Point your AI agent at freehire and let it find you a job.

Get the CLI →

Inworld

Discussion
8 jobs
Inworld
1 views 2 days ago

Founding AI Solutions Engineer - USA

NewBe an early applicant HybridNorth AmericaFull-time
United States

Founding solutions engineer at an AI inference startup: leads technical discovery, runs POCs, and guides enterprise customers from signing to production using Inworld's TTS, STT, LLM inference, and realtime APIs. Requires hands-on coding (Python preferred), deep AI/ML API fluency, and a hybrid on-site presence in Mountain View.

AI API Backbone.js Cloud Containerization +11 skills
170K – 250K $
 Sign in to see your match
Apply
Inworld
1 views 2 days ago

Staff / Principal Machine Learning Engineer, Inference - USA

NewBe an early applicant HybridNorth AmericaFull-timePrincipal
United States

Inworld, an AI research lab and inference provider serving realtime LLM/speech models at massive scale (10T+ tokens/month), is hiring a Staff/Principal ML Engineer in Mountain View to optimize model inference and serving infrastructure. Core work spans serving frameworks like vLLM/TRT-LLM, GPU performance tuning in C++/CUDA/Rust, and distributed scaling on Kubernetes/Ray. Onsite role with relocati

Agentic AI AI API C++ CUDA +8 skills
270K – 500K $
 Sign in to see your match
Apply
Inworld
3 views 2 days ago

Staff / Principal Machine Learning Engineer, Inference - UK

NewBe an early applicant RemoteUKFull-timePrincipal
United Kingdom

Staff/Principal ML Engineer optimizing realtime LLM inference at Inworld: taking speech and LLM models from research into high-volume production serving, squeezing latency and throughput out of NVIDIA GPUs with frameworks like vLLM/TRT-LLM, C++/CUDA/Rust, and Kubernetes/Ray at trillion-token monthly scale. UK-based, remote; no visa sponsorship for this role.

Agentic AI AI API C++ CUDA +8 skills
140K – 200K £
 Sign in to see your match
Apply
Inworld
3 views 2 days ago

Staff / Principal Machine Learning Engineer, Inference - Switzerland

NewBe an early applicant RemoteEuropeFull-timePrincipal
Switzerland

Inworld is hiring a Staff/Principal ML engineer to optimize and scale realtime AI inference — taking first-party speech and LLM models from research into high-volume production serving. Core work is GPU inference optimization (vLLM/TRT-LLM, quantization, batching) and distributed serving with C++/CUDA/Rust/Python, remote within Switzerland.

Agentic AI AI API C++ CUDA +8 skills
 Sign in to see your match
Apply
Inworld
4 views 2 days ago

Senior / Lead Machine Learning Engineer, Inference - Serbia

NewBe an early applicant RemoteEuropeFull-timeLead

Senior/Lead machine learning engineer optimizing realtime LLM and speech-model inference at Inworld, an AI research lab and inference provider. Day to day: tune serving frameworks like vLLM/TRT-LLM, apply quantization and batching, profile C++/CUDA/Rust code, and scale multi-GPU Kubernetes/Ray serving.

Agentic AI AI API C++ CUDA +8 skills
 Sign in to see your match
Apply
Inworld
2 views 2 days ago

Staff / Principal Platform Engineer - USA

NewBe an early applicant HybridNorth AmericaFull-timePrincipal
United States

Staff/Principal Platform Engineer at Inworld, an AI lab building top-ranked realtime voice models. Owns cloud infrastructure for TTS and LLM Router services: Kubernetes, Terraform/ArgoCD, CI/CD pipelines, monitoring, and AI-powered developer tooling. On-site in the South Bay (Mountain View) a few days a week.

AI Ansible API Argo CD Azure +15 skills
280K – 350K $
 Sign in to see your match
Apply
Inworld
2 views 2 days ago

Staff / Principal Software Engineer - USA

NewBe an early applicant HybridNorth AmericaFull-timePrincipal
United States

Staff/Principal backend engineer at Inworld building its realtime voice AI platform: the Inworld Router (single API routing across 200+ LLMs with failover and cost/latency-based routing), Realtime API, TTS/STT model services, and platform infrastructure. IC-focused role using statically typed backend languages like Go, Python, C++, or Rust.

AI Analytics API ClickHouse Cloud +14 skills
280K – 350K $
 Sign in to see your match
Apply
Inworld
3 views 2 days ago

Staff / Principal Software Engineer - Canada

NewBe an early applicant RemoteNorth AmericaFull-timePrincipal
Canada

Staff/Principal backend engineer at Inworld, a realtime AI research lab and inference provider, building core platform systems: the Inworld Router (multi-provider LLM routing with failover, cost/latency optimization), realtime APIs, and TTS/STT model services. Backend work in Go/Python/C++/Rust with cloud-scale serving, relational DBs, caching, and data pipelines.

AI Analytics API ClickHouse Cloud +14 skills
180K – 260K CAD
 Sign in to see your match
Apply

Tailor your CV for this role?

We couldn't check your fit for this role — add a CV to your profile to see it next time.