Senior ML Engineer — Production ML & Inference (Remote)

Invoca; Chicago (IL); Remote; USD 152,000 - 228,000; Full time

Benefits offered by this job

Flexible Time Off

Paid Holidays

Health Benefits

401(k) Match

Stock Options

Mental Health Program

Paid Family Leave

Paid Medical Leave

Wellness Subsidy

Job summary

Invoca is seeking a Senior ML Engineer to own the production ML stack, turning trained models into high-throughput services used by data scientists, AI engineers, and product teams. You will optimize inference, deploy pipelines, and collaborate across data science and product groups to ship reliable AI features.

You will work on end-to-end ML infrastructure, with emphasis on latency, throughput, and cost, while advancing transformer-based NLP models and parameter-efficient fine-tuning in

Qualifications

• 5+ years of ML engineering with a strong production focus.
• Advanced Python and deep learning proficiency (PyTorch, Transformers).
• Experience deploying transformer-based NLP models in production.

Responsibilities

• Own production ML as a system: CI/CD for ML artifacts, evaluation, versioning, deployment.
• Own end-to-end inference infrastructure: model serving on Triton, Baseten, and Kubernetes-based GPU infra.
• Tune for low latency and high throughput; build scalable APIs for internal/external access.
• Contribute to model training infra, data pipelines, and data lake foundations.
• Build evaluation/monitoring practices to catch regressions before customers.

Skills

ML engineering

Advanced Python

PyTorch

HuggingFace Transformers

spaCy

NLP model deployment

MLOps tooling

APIs for ML

Kubernetes

Triton Inference Server

Education

B.S. in Computer Science/Engineering

Tools

Triton Inference Server

Baseten

vLLM

Kubernetes

MLflow

Braintrust

Job description

Invoca is seeking a Senior ML Engineer to own the production ML stack, turning trained models into high-throughput services used by data scientists, AI engineers, and product teams. You will optimize inference, deploy pipelines, and collaborate across data science and product groups to ship reliable AI features.

You will work on end-to-end ML infrastructure, with emphasis on latency, throughput, and cost, while advancing transformer-based NLP models and parameter-efficient fine-tuning in