Senior ML Engineer - Production Pipelines (Remote)

Canals; New York (NY); On-site; USD 150,000 - 210,000; Full time

Job summary

Canals is seeking a senior‑level Machine Learning Engineer to move quickly while delivering high‑quality, end‑to‑end ML pipelines that automate logistics for our wholesale distributor customers.

You will own projects from problem definition through data exploration, model deployment, and production monitoring, collaborating with engineering teams and mentoring others to raise the bar on reproducibility and performance.

Qualifications

• Senior‑level experience building and deploying ML models in production.
• Experience designing scalable data pipelines with large datasets.
• Strong ownership mindset and ability to deliver measurable customer value.
• Proficiency in Python with ML frameworks (scikit‑learn, PyTorch, TensorFlow) and data tools (Pandas, Spark).
• Ability to provide code reviews and architectural feedback.
• Comfort working independently in a fast‑paced product environment.
• Experience in high‑growth startups or small teams is a plus.
• Familiarity with MLOps practices is a plus.

Responsibilities

• Design, build, and maintain scalable ML models for logistics processes.
• Own projects end‑to‑end from problem formulation to deployment.
• Collaborate with engineering to align ML work with customer needs.
• Mentor teammates and enforce reproducible, high‑quality code.
• Evaluate tools/frameworks to improve ML infra.
• Help shape Canals' future as we scale with customers.

Skills

Python

ML Frameworks

Data Pipelines

Production ML

Mentoring

Independent Work

Tools

PyTorch

TensorFlow

Pandas

Spark

Job description

Canals is seeking a senior‑level Machine Learning Engineer to move quickly while delivering high‑quality, end‑to‑end ML pipelines that automate logistics for our wholesale distributor customers.

You will own projects from problem definition through data exploration, model deployment, and production monitoring, collaborating with engineering teams and mentoring others to raise the bar on reproducibility and performance.