Senior ML Engineer — Multimodal Vision & Real‑Time Inference

Engai; New York (NY); Remote; USD 140,000 - 190,000; Full time

Benefits offered by this job

Full healthcare coverage

Mental wellness stipend

Generous hardware allowance (M3 Max)

Job summary

Engai is seeking a Machine Learning Engineer — Multimodal & Vision to advance autonomous driving datasets by deploying advanced labeling models and zero-shot architectures. You will optimize end-to-end inference in production and work with global teams on scalable ML solutions.

You will fine-tune models such as SAM, YOLO, Mask R-CNN, and 3D detectors, and integrate model-assisted annotation APIs into customer MLOps infra while benefiting from flexible work hours and generous hardware support.

Qualifications

• 3+ years building and deploying deep learning models in production.
• Experience with computer vision or multimodal architectures.
• Strong Python and cloud experience (AWS/GCP).

Responsibilities

• Fine-tune and deploy assisted pre-labeling vision models (SAM, YOLO, Mask R-CNN, 3D point cloud detectors).
• Optimize model inference latency on GPU clusters using NVIDIA TensorRT, ONNX, and Triton.
• Evaluate model prediction confidence against human consensus to tighten the active learning loop.
• Integrate model-assisted annotation APIs into customer MLOps infrastructure.

Skills

Computer Vision & ML

Cloud systems

Real-time inference optimization

Tools

PyTorch

Docker

CUDA

ONNX

NVIDIA TensorRT

Triton

YOLO

Mask R-CNN

Job description

Engai is seeking a Machine Learning Engineer — Multimodal & Vision to advance autonomous driving datasets by deploying advanced labeling models and zero-shot architectures. You will optimize end-to-end inference in production and work with global teams on scalable ML solutions.

You will fine-tune models such as SAM, YOLO, Mask R-CNN, and 3D detectors, and integrate model-assisted annotation APIs into customer MLOps infra while benefiting from flexible work hours and generous hardware support.