[All remote jobs](https://jobicy.com/jobs.md)[![Cantina Labs logo](https://jobicy.com/data/server-nyc0409/galaxy/mercury/2026/11/e52bb5e84323-221.webp)](https://jobicy.com/company/cantina-labs.md)[Cantina Labs](https://jobicy.com/company/cantina-labs.md) # Machine Learning Engineer, Ops AI Summary Cantina Labs is seeking a Machine Learning Engineer to own the production inference stack for real-time text-to-speech and speech-recognition models. The role spans GPU inference optimization, streaming serving systems, Kubernetes operations, CI/CD, benchmarking, and accuracy regression validation. The engineer will partner closely with research teams to productionize model checkpoints while owning latency, throughput, cost efficiency, and reliability. Strong hands-on expertise in Python, PyTorch, CUDA profiling, model-serving frameworks, and production cloud infrastructure is central to success. This is a senior, highly technical engineering position focused on scalable speech AI operations.[Apply for this job](#job-application)[View company](https://jobicy.com/company/cantina-labs.md)ShareRemote from[USA](https://jobicy.com/job-region/usa.md), [Europe](https://jobicy.com/job-region/europe.md)SalaryUndisclosedDepartment[Software Engineering](https://jobicy.com/categories/engineering.md)EmploymentFull TimeExperienceOpen levelPublished10 Nov 2026Apply before10 Dec 2026Listing views55Application actions4Application toolkit ## Make your next move. Prepare your resume, explore your fit, and draft a cover letter for this opportunity. Opportunity details ## About this role. ### About Cantina: [Cantina Labs](https://jobicy.com/company/cantina-labs.md) is a social AI company, developing a suite of advanced real-time models that push the boundaries of expression, personality, and realism. We bring characters to life, transforming how people tell stories, connect, and create. We build and power ecosystems. Cantina, our flagship social AI platform, is just the beginning. If you’re excited about the potential AI has to shape human creativity and social interactions, join us in building the future! ### About the Role: We are looking for an ML Engineer to own the production inference stack for our text-to-speech (TTS) and speech recognition (ASR) models, end to end. Our research team delivers trained model checkpoints; you will productionize them as low-latency, real-time streaming services that run cost-efficiently on GPUs. The role covers the inference engines, the Kubernetes infrastructure they run on, and the performance benchmarking and accuracy validation that let us ship changes safely. You will bridge research and production, and own latency, throughput, cost and accuracy as we scale. ### What You’ll Do: * Build and optimize streaming inference engines for TTS and ASR models, including multi-stage model pipelines. * Optimize latency (time to first chunk, p50/p99) and throughput using continuous batching, CUDA Graphs, torch.compile and mixed precision. * Maintain numerical parity with the reference implementation through automated accuracy regression tests, per stage and end to end. * Deploy and operate GPU inference services on Kubernetes: autoscaling, containerization and infrastructure as code. * Build CI/CD for model artifacts, with model versioning and reproducible releases. * Own observability and performance benchmarking: p50/p99 latency, real-time factor (RTF), GPU utilization and cost per request. * Partner with research to productionize new models. ### What You’ll Bring: * Hands-on experience deploying, scaling and optimizing ML models in production, beyond consuming model APIs. * Working knowledge of the full inference stack, from CUDA kernels to serving frameworks, with depth in some layers; expertise across all of them is not expected. * GPU performance optimization: profiling (Nsight Systems, PyTorch Profiler), memory bandwidth, CPU-GPU synchronization. * Solid understanding of model serving: continuous batching, KV cache management, request scheduling. * Production experience with Kubernetes, CI/CD and cloud infrastructure. * Strong Python and PyTorch, and a rigorous approach to performance benchmarking. * Experience with speech or audio models (TTS, ASR, voice conversion). * Experience with inference frameworks such as vLLM (vLLM-Omni), SGLang, TensorRT-LLM, TensorRT or Triton Inference Server. ### Compensation: When determining compensation, a number of factors will be considered, including skills, experience, job scope, location, and competitive compensation market data. ### Benefits for U.S.-based roles: * Competitive salary and generous company equity * Medical, dental, and vision insurance – 99.99% of premiums covered by Cantina * 42 days of paid time off, including: 15 PTO days * 10 sick days * 15 company holidays * 2 floating holidays * Generous parental leave & fertility support * 401(k) retirement savings plan * Lifestyle spending account – $500/month to use however you’d like * Complimentary lunch and snacks for in-office employees * One Medical membership, and more! Show more [Apply now >](https://jobicy.com/jobs/160996-machine-learning-engineer-ops.md) > Annual salary information is not provided for this position. Explore salary ranges for similar roles in our [Salary Directory ›](https://jobicy.com/salaries.md) * ![Upload CV](data:image/svg+xml;base64,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) ### Upload your resume now To unlock remote work opportunities and be discovered by global employers. This job listing has been manually reviewed by the Jobicy Trust & Safety Team for compliance with our posting guidelines, including verification of the company's legitimacy, accuracy of job details, clarity of remote work policy, and absence of misleading or fraudulent content. ## Role DNA A quick view of the complexity, pace, ownership and collaboration implied by the job description. ### Job Complexity 5/5EasyHard ### Pace & Pressure 5/5RelaxedFast-paced ### Autonomy Level 5/5GuidedFull ownership ### Communication Load 4/5IndependentCollaborative AI insightThe role requires deep cross-stack expertise, from CUDA and GPU performance behavior through model-serving systems and Kubernetes production operations. Success depends on independently balancing real-time latency, model accuracy, reliability, and infrastructure cost. ## Salary analysis Estimated compensation compared with the broader US market for similar roles. Estimated job median (per year)Market rate$190,000US market range (per year)$150k–$240k0$264k AI insightThe yearly pay period is inferred from the job context; it was not explicitly stated by the employer. No employer base-pay amount is disclosed. The annual USD figures are estimated market compensation for a senior ML inference and GPU-optimization engineer in the United States; the yearly period is inferred from the full-time professional role and typical market convention. ## Core skills Skills and capabilities most closely associated with this opportunity. [Machine Learning Engineering](https://jobicy.com/jobs?search_keywords=Machine%20Learning%20Engineering.md)[GPU Inference Optimization](https://jobicy.com/jobs?search_keywords=GPU%20Inference%20Optimization.md)[PyTorch](https://jobicy.com/jobs?search_keywords=PyTorch.md)[Python](https://jobicy.com/jobs?search_keywords=Python.md)[CUDA](https://jobicy.com/jobs?search_keywords=CUDA.md)[Kubernetes](https://jobicy.com/jobs?search_keywords=Kubernetes.md)[Model Serving](https://jobicy.com/jobs?search_keywords=Model%20Serving.md)[Speech Recognition](https://jobicy.com/jobs?search_keywords=Speech%20Recognition.md)[Text-to-Speech](https://jobicy.com/jobs?search_keywords=Text-to-Speech.md)[TensorRT](https://jobicy.com/jobs?search_keywords=TensorRT.md)[Triton Inference Server](https://jobicy.com/jobs?search_keywords=Triton%20Inference%20Server.md)[CI/CD](https://jobicy.com/jobs?search_keywords=CICD.md)[Performance Benchmarking](https://jobicy.com/jobs?search_keywords=Performance%20Benchmarking.md)[Infrastructure as Code](https://jobicy.com/jobs?search_keywords=Infrastructure%20as%20Code.md)[Observability](https://jobicy.com/jobs?search_keywords=Observability.md) Sample interview questionsHow would you reduce p99 latency for a streaming TTS or ASR inference service?I would first establish traces and benchmarks that isolate queueing, preprocessing, GPU execution, postprocessing, and network streaming time. I would profile GPU kernels and synchronization points, then test batching policies, mixed precision, CUDA Graphs, compilation, memory reuse, and model-specific pipeline parallelism while protecting output quality. How do you validate that an optimized inference engine preserves model accuracy? I would create a versioned regression suite containing representative and edge-case inputs, with per-stage and end-to-end comparisons against the reference implementation. Acceptance thresholds should cover numerical tolerances as well as task-specific measures such as transcription error rate, audio quality checks, and behavioral output consistency. What factors would you consider when designing autoscaling for GPU model-serving workloads on Kubernetes? I would use demand and performance signals such as queue depth, concurrent requests, GPU utilization, latency percentiles, and real-time factor rather than CPU utilization alone. The design should account for model-loading time, warm capacity, GPU node availability, batching behavior, and safe scale-down rules that avoid interrupting active streams. How would you decide whether continuous batching improves a real-time speech service? I would compare it with static and request-by-request execution under realistic traffic distributions. The decision would be based on throughput, time to first chunk, p50 and p99 latency, GPU utilization, memory pressure, and quality parity, with batch windows constrained so they do not harm interactive responsiveness. Describe a reliable release process for new model artifacts and inference-runtime changes. I would version models, containers, configuration, and benchmark datasets together, then run automated accuracy, load, and compatibility tests in CI. Releases should use staged deployment or canaries, monitored against latency, error rate, GPU utilization, and cost metrics, with a documented rollback path to a known-good model and runtime version. Next step ## Apply now. Follow the employer’s application method and review Jobicy’s safety guidance before sharing personal information. Keep exploring ## Related remote jobs. * ![Orkes logo](https://jobicy.com/data/server-nyc0409/galaxy/mercury/2026/11/71ddcab7b4b8-221.webp) Orkes Nov 10 New ### [Solutions Architect](https://jobicy.com/jobs/161091-solutions-architect-5.md) Who We Are Building the Backbone of Distributed Applications. Orkes is building the platform that powers the next generation of enterprise applications and AI systems. Founded by the creators of… * ![Reedsy logo](https://jobicy.com/data/server-nyc0409/galaxy/mercury/2026/11/e158be7d0de8-221.webp) Reedsy Nov 10 New ### [Quality Assurance Engineer – Remote Europe](https://jobicy.com/jobs/161089-quality-assurance-engineer-remote-europe.md) We welcome applicants based anywhere in Europe. About Reedsy We’re here to give authors the tools and resources they need to create beautiful books. Our marketplace gathers the industry’s best… * ![Firework logo](https://jobicy.com/data/server-nyc0409/galaxy/mercury/2026/11/70ffd1e7b581-221.webp) Firework Nov 10 New ### [AI Content Specialist](https://jobicy.com/jobs/161081-ai-content-specialist.md) About Firework Join Firework – Where Innovation Meets Impact Firework is redefining the future of commerce as an AI and video commerce company — combining cutting-edge technology, an exclusive network… * ![PubNub logo](https://jobicy.com/data/server-nyc0409/galaxy/mercury/2026/11/088f69f1f5d6-221.webp) PubNub Nov 10 New ### [Senior GTM Engineer](https://jobicy.com/jobs/161067-senior-gtm-engineer.md) Location: Poland, Remote Employment Type: Full-time, B2B ContractCompensation: PLN 12,000–22,000 net + VAT per month About PubNub PubNub powers real-time interactive experiences that drive engagement, retention, and monetization. Our market-leading… * ![Elevenlabs logo](https://jobicy.com/data/server-nyc0409/galaxy/mercury/2025/06/e01b4c5d-221.png) Elevenlabs Nov 10 New ### [Full-Stack Engineer – ElevenAPI](https://jobicy.com/jobs/161065-full-stack-engineer-elevenapi.md) About ElevenLabs ElevenLabs is an AI research and product company transforming how we interact with technology. We launched in January 2023 with the first human-like AI voice model. Today, we… * ![Filigran logo](https://jobicy.com/data/server-nyc0409/galaxy/mercury/2026/11/7b905d81717f-221.webp) Filigran Nov 10 New ### [Senior Software Engineer — AI-Native Engineering (XTM Foundation)](https://jobicy.com/jobs/161063-senior-software-engineer-ai-native-engineering-xtm-foundation.md) 🌀 The Company Founded in 2022, Filigran is a global cybersecurity company on a mission to empower defense teams to be proactive through open-source solutions that uncover threats and drive… * ![Deepgram logo](https://jobicy.com/data/server-nyc0409/galaxy/mercury/2020/12/WRILS-201212160008-406229.jpg) Deepgram Nov 10 New ### [Senior Forward Deployed Engineer (FDE), Strategic Accounts](https://jobicy.com/jobs/161057-senior-forward-deployed-engineer-fde-strategic-accounts.md) Company Overview Deepgram is bringing the world’s most natural interface, voice, to the technology we use every day. Our speech models and real-time infrastructure power AI systems that keep up… * ![Deepgram logo](https://jobicy.com/data/server-nyc0409/galaxy/mercury/2020/12/WRILS-201212160008-406229.jpg) Deepgram Nov 10 New ### [Staff Web Engineer, Marketing](https://jobicy.com/jobs/161047-staff-web-engineer-marketing.md) Company Overview Deepgram is bringing the world’s most natural interface, voice, to the technology we use every day. Our speech models and real-time infrastructure power AI systems that keep up… * ![Caylent logo](https://jobicy.com/data/server-nyc0409/galaxy/mercury/2025/06/9ed8d81b-221.jpg) Caylent Nov 10 New ### [Senior Forward Deployed Engineer](https://jobicy.com/jobs/161041-senior-forward-deployed-engineer-3.md) Caylent is an AI-first cloud services company that helps organizations turn ambitious ideas into meaningful business impact. As an AWS Premier Tier Services Partner and a charter member of Anthropic’s… * ![PubNub logo](https://jobicy.com/data/server-nyc0409/galaxy/mercury/2026/11/088f69f1f5d6-221.webp) PubNub Nov 10 New ### [Developer Advocate, Blocks.ai](https://jobicy.com/jobs/160992-developer-advocate-blocks-ai.md) Location: Poland – RemoteEmployment Type: Full-time, B2B ContractCompensation: PLN 12,000–22,000 net + VAT per month (B2B) About PubNub PubNub powers real-time interactive experiences that drive engagement, retention, and monetization. Our… [Browse all jobs](https://jobicy.com/jobs.md)