机器学习运维基础设施工程师
ML Ops Infrastructure Engineer
## **公司简介**
Deepgram 是支撑新兴数千亿美元语音 AI 经济的领先平台，提供实时 API 用于语音转文本（STT）、文本转语音（TTS），并可大规模构建生产级语音代理。超过 20 万名开发者和 1,300 多家机构使用“由 Deepgram 提供支持”的语音服务，包括 Twilio、Cloudflare、Sierra、Decagon、Vapi、Daily、Cresta、Granola 和 Jack in the Box。Deepgram 的语音原生基础模型通过云 API 或自托管及本地软件访问，具有无与伦比的准确性、低延迟和成本效率。由领先的全球投资者和战略合作伙伴牵头的最新 C 轮融资支持，Deepgram 已处理超过 5 万年的音频，并转录了超过 1 万亿个单词。世界上没有哪家公司比 Deepgram 更了解语音。
## **公司运营节奏**
在 Deepgram，我们期望具备 AI 优先的思维模式——AI 的使用和熟悉度不是可选的，而是我们运作、创新和衡量绩效的核心。
在 Deepgram 工作的每位团队成员都应积极使用和尝试先进的 AI 工具，甚至将你自己的工具融入日常工作中。我们衡量 AI 在实际成果中的应用效果，持续且富有创意地利用最新 AI 能力是这里成功的关键。候选人应能够快速采用新模型和新模式，将 AI 整合到工作流程中，并不断推动这些技术的边界。
此外，我们以 AI 的速度前进。变化迅速，你可以预期你的日常工作也会同样快速地演变。如果你对实验、适应、临场思考和持续学习不感兴趣，或者你寻求的是高度规范化的传统 9 到 5 的工作，那么这可能不是适合你的职位。
### **机会介绍**
将一个研究笔记本中的模型转化为服务于数百万请求的生产 API 是 AI 领域最困难的问题之一。作为 Deepgram 的 ML 运维基础设施工程师，你将负责连接研究与生产之间的关键桥梁——构建将模型从实验状态转化为经过实战验证的规模化管道、部署系统和测试基础设施。你的工作确保我们研究团队的每个模型改进都能安全、快速、可靠地交付给依赖 Deepgram API 进行实时语音 AI 的客户。
### **你将负责**
- 设计
查看英文原文
## **Company Overview**
Deepgram is the leading platform underpinning the emerging trillion-dollar Voice AI economy, providing real-time APIs for speech-to-text (STT), text-to-speech (TTS), and building production-grade voice agents at scale. More than 200,000 developers and 1,300+ organizations build voice offerings that are ‘Powered by Deepgram’, including Twilio, Cloudflare, Sierra, Decagon, Vapi, Daily, Cresta, Granola, and Jack in the Box. Deepgram’s voice-native foundation models are accessed through cloud APIs or as self-hosted and on-premises software, with unmatched accuracy, low latency, and cost efficiency. Backed by a recent Series C led by leading global investors and strategic partners, Deepgram has processed over 50,000 years of audio and transcribed more than 1 trillion words. There is no organization in the world that understands voice better than Deepgram.
## **Company Operating Rhythm**
At Deepgram, we expect an AI-first mindset—AI use and comfort aren’t optional, they’re core to how we operate, innovate, and measure performance.
Every team member who works at Deepgram is expected to actively use and experiment with advanced AI tools, and even build your own into your everyday work. We measure how effectively AI is applied to deliver results, and consistent, creative use of the latest AI capabilities is key to success here. Candidates should be comfortable adopting new models and modes quickly, integrating AI into their workflows, and continuously pushing the boundaries of what these technologies can do.
Additionally, we move at the pace of AI. Change is rapid, and you can expect your day-to-day work to evolve just as quickly. This may not be the right role if you’re not excited to experiment, adapt, think on your feet, and learn constantly, or if you’re seeking something highly prescriptive with a traditional 9-to-5.
### **The Opportunity**
Getting a model from a research notebook to a production API serving millions of requests is one of the hardest problems in AI. As an ML Ops Infrastructure Engineer at Deepgram, you will own the critical bridge between research and production -- building the pipelines, deployment systems, and testing infrastructure that take models from experimental to battle-tested at scale. Your work ensures that every model improvement our research team makes can be safely, quickly, and reliably delivered to the customers who depend on Deepgram's APIs for real-time voice AI.
### **What You'll Do**
- Design and build CI/CD pipelines specifically tailored for ML model development, validation, and deployment
- Architect and maintain model deployment pipelines that move models from research environments through staging to production with confidence
- Build A/B testing infrastructure that enables controlled rollouts of new models and measures real-world performance impact
- Implement comprehensive monitoring for model performance in production -- accuracy metrics, latency, drift detection, and regression alerts
- Develop automated retraining pipelines that trigger on data changes, performance degradation, or scheduled cadences
- Create and maintain build and test environments that mirror production, giving researchers high-fidelity feedback before deployment
- Establish model versioning, artifact management, and rollback capabilities to ensure safe and reproducible deployments
- Collaborate with research engineers to define and enforce model quality gates before production promotion
- Build observability dashboards that give the team real-time insight into model health across all environments
- Optimize model serving infrastructure for latency, throughput, and cost efficiency
### **You'll Love This Role If You**
- Are excited by the challenge of operationalizing cutting-edge AI models at production scale
- Believe that great infrastructure is what turns research breakthroughs into customer value
- Enjoy designing systems that are automated, reliable, and self-healing
- Want to work on problems where minutes of latency reduction or percentage points of accuracy matter enormously
- Like collaborating across research and engineering teams to make the whole organization faster
- Are motivated by building the deployment and testing systems that back a platform serving over 200,000 developers
### **It's Important To Us That You Have**
- 4+ years of experience in MLOps, DevOps, or infrastructure engineering with a focus on ML systems
- Strong proficiency in Python and experience building automation and tooling for ML workflows
- Deep experience with CI/CD systems and building pipelines for software and model delivery
- Hands-on experience with Docker and Kubernetes for containerized workload management
- Practical experience deploying and serving ML models in production environments
- Familiarity with model evaluation, validation, and quality assurance processes
- Understanding of monitoring and observability principles as applied to ML systems
- Strong problem-solving skills and a bias toward automation over manual processes
### **It Would Be Great If You Had**
- Experience with model serving frameworks such as NVIDIA Triton Inference Server, TensorRT, or ONNX Runtime
- Background in speech, audio, or real-time media ML systems
- Experience with Infrastructure as Code tools such as Terraform or Pulumi
- Hands-on experience with monitoring and observability stacks (Prometheus, Grafana, Datadog, or similar)
- Familiarity with GPU-accelerated inference optimization and profiling
- Experience with feature stores, data versioning, or ML metadata management
- Knowledge of canary deployment strategies and progressive delivery for ML models
_**Notice**: We're aware of individuals impersonating Deepgram recruiters. All legitimate Deepgram recruiting communication comes from an @_ [_deepgram.com_](http://deepgram.com) _email address. If you've received a message claiming to be Deepgram, please forward it to careers@deepgram.com._