Production ML Engineer — In-Office NYC, Scale & Inference

Digital Waffle; New York (NY); On-site; USD 140,000 - 190,000; Full time

Job summary

Digital Waffle in New York is hiring an ML Engineer to take models from notebook to production and keep them performant and affordable at scale. You will own training, serving, evaluation and the plumbing underneath, sitting at the intersection of ML and engineering.

The role requires strong Python and PyTorch experience, experience with Hugging Face Transformers, and hands-on model serving with GPUs. This position is in-office 5 days/week in New York.

Qualifications

• Proficient Python and PyTorch with production ML experience.
• Experience with Hugging Face Transformers and distributed training.
• Hands-on with model serving stacks (vLLM, Triton, TensorRT) and GPU optimization.
• Familiarity with experiment tracking (MLflow, Weights & Biases) and reproducibility.
• Cloud experience (AWS/GCP/Azure) and modern infra tooling.

Responsibilities

• Train, fine-tune and serve models in production using Python and PyTorch.
• Build and maintain the inference stack: model serving (vLLM, Triton, custom), batching, caching, cost control.
• Stand up training infrastructure using Ray, Modal, SageMaker or similar.
• Work with vector databases (pgvector, Pinecone, Weaviate) for retrieval-heavy workloads.
• Build evaluation pipelines so model quality is measurable rather than anecdotal.
• Partner with product and AI engineers to turn research or OSS models into shipped features.
• Own GPU utilization, latency and inference cost as first-class concerns.
• Use AI tooling (Claude, Cursor and similar) across every part of your workflow.

Skills

Python

PyTorch

Hugging Face Transformers

Distributed training

Experiment tracking

Tools

vLLM

Triton

TensorRT

Ray

Modal

SageMaker

Weights & Biases

MLflow

AWS

GCP

Azure

Job description

Digital Waffle in New York is hiring an ML Engineer to take models from notebook to production and keep them performant and affordable at scale. You will own training, serving, evaluation and the plumbing underneath, sitting at the intersection of ML and engineering.

The role requires strong Python and PyTorch experience, experience with Hugging Face Transformers, and hands-on model serving with GPUs. This position is in-office 5 days/week in New York.