Production ML Engineer: Turn Research into Scalable Models

Deepgram, Inc.; Northern (KY); Hybrid; USD 140,000 - 190,000; Full time

Job summary

Deepgram, Inc. is building the real-time speech AI stack for a trillion-dollar market. We are seeking an Applied ML Engineer to own the research-to-production pipeline, collaborating with researchers to deploy models at scale across our hybrid infrastructure.

You will design release gates, optimize inference, and build tooling to accelerate production-ready AI. Strong Python, PyTorch, and systems experience are essential, with a track record shipping ML at scale.

Qualifications

• Strong software engineering fundamentals, with proficiency in Python and production-quality ML code.
• Hands-on experience taking ML models from research or prototype stage into production at scale.
• Familiarity with serving and inference optimization for production workloads.

Responsibilities

• Own the research-to-production pipeline: turn research checkpoints into production models and define the path to deployment.
• Partner with researchers to productionize new models, translating experimental code into robust, reproducible workflows.
• Build tooling and abstractions to move models through training, evaluation, packaging, and deployment with minimal friction.
• Design and own model release gates with automated evaluation, regression detection, and quality checks for shipping models.
• Optimize models and serving for production: efficient inference, batching, memory and latency tuning.
• Strengthen the build and delivery layer for models on our hybrid infrastructure (GPU data centers and cloud).
• Establish benchmarking and validation across development to production to catch regressions early.
• Build feedback loops to surface what's working and drive the next iteration.

Skills

Python

PyTorch

ML pipelines

Distributed systems

Production ML

Tools

CI/CD for ML

Model packaging

Job description

Deepgram, Inc. is building the real-time speech AI stack for a trillion-dollar market. We are seeking an Applied ML Engineer to own the research-to-production pipeline, collaborating with researchers to deploy models at scale across our hybrid infrastructure.

You will design release gates, optimize inference, and build tooling to accelerate production-ready AI. Strong Python, PyTorch, and systems experience are essential, with a track record shipping ML at scale.