Join Cantina as an MLOps Engineer to build and scale inference infrastructure for generative audio models.
Posted by employer 3 months ago
First seen on Joblaze 1 month ago
Last verified on the company career page 1 day ago
Skills & Technologies
Not disclosed in this posting: years of experience, work arrangement, visa sponsorship.
Benefits
Joblaze summary
The Machine Learning Engineer in Operations at Cantina focuses on building and scaling the inference infrastructure for generative audio models, ensuring efficient model serving for both streaming and batch applications. Key skills include expertise in Kubernetes for orchestration, MLOps practices, and a solid understanding of audio model architectures like TTS and ASR. This role is ideal for someone with a strong technical background in software engineering and experience in high-performance systems. Cantina's innovative environment emphasizes collaboration between research and production teams to enhance audio model performance.
Joblaze insights
- Listed about a month ago — first seen on Joblaze September 3, 2026. Last confirmed on Cantina's careers page October 27, 2026.
- Salary band is below the typical range for AI/ML roles (median ~$190,000).
- Starts above 26% of 148 comparable mid ai/ml roles that list Python we track (median $150,000 across 56 companies). See Python salary trends
- Python appears in 47.3% of 831 comparable mid ai/ml roles; Text-to-Speech appears in 0.1% of 831 comparable mid ai/ml roles.
Quick facts
- What's the salary range?
- Cantina lists $125,000–$165,000 for this role.
- What's the tech stack?
- Joblaze extracted these technologies from the posting: CI/CD, GPU, Go, Kubernetes, MLOps, Python.
- What seniority level is this role?
- Cantina targets mid-level candidates for this position.
- Is this full-time or contract?
- Full-time for this Machine Learning Engineer, Ops role at Cantina.
From the original posting
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
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
Complimentary lunch and snacks for in-office employees
One Medical membership, and more!
Standard company text repeated across Cantina's postings is omitted here.