ML Engineer, Product

Mach9 Robotics Inc.; San Francisco (CA); On-site; USD 120,000 - 180,000; Full time

Job summary

Mach9 Robotics Inc. is seeking an early-career ML Engineer to build perception models for our AI-enabled CAD system. You will extract 3D object and line features from LiDAR and imagery, train models, and ship new features end-to-end from data strategy to evaluation.

You will work closely with customers to develop CV/ML pipelines, adapt models to new sensor types, and contribute to production deployments for field surveyors and engineers.

Qualifications

• BS or MS in Computer Science, Electrical Engineering, Robotics, or a related field.
• Strong coding abilities (Python + PyTorch) and comfortable with a large codebase.
• Hands-on experience training or fine-tuning a vision model (segmentation, detection, or 3D).
• Working knowledge of geometry for 3D perception: coordinates, transforms, projecting between images and point clouds.
• Curiosity and speed: rapidly learning new frameworks and papers and explaining learnings.
• Clear communicator with engineers, product, and surveyors who use what you build.
• Fluent with AI coding assistants.

Responsibilities

• Ship new extraction features end to end: scoping with product and customer-facing teams, data and labeling strategy, model selection or fine-tuning, evaluation, and integration into Digital Surveyor.
• Build on existing model families and open-source tooling first (vision foundation models, VLMs, point-cloud backbones, classical geometry) and know what's out there.
• Adapt production models to new object classes, regions, and sensor types as customers bring them.
• Build evaluation pipelines that measure improvements and regression alike.
• Iterate on feature extraction pipelines according to customer feedback and metrics changes.

Skills

Python

PyTorch

Vision model training

3D geometry knowledge

Communication

AI coding assistants

Education

BS/MS in CS/EE/Robotics or related

Tools

Open3D

PDAL

PyTorch3D

Sparse convolution

ONNX/TensorRT

Job description

The role

At Mach9, ML Engineers build the perception models at the core of our AI-enabled CAD system. We build models to extract 3D object and line features from dense LiDAR point clouds and imagery. Our unique data advantage allows us to develop and train cutting edge 3D scene understanding models that serve real surveyors and engineers in the field.

This role is product-focused. You will be working closely with customers to develop CV/ML pipelines and workflows that solves their problems. Your responsibility is to ship new features and product lines end-to-end from data strategy, to model training, to evaluation.

This role is ideal for early-career engineers (new grad to ~3 years) who learn fast, are curious about how things work, and get real satisfaction from shipping. You need to be able to come up with ideas, try them, get feedback and iterate quickly.

Responsibilities

• Ship new extraction features end to end: scoping with product and customer-facing teams, data and labeling strategy, model selection or fine-tuning, evaluation, and integration into Digital Surveyor.

• Build on existing model families and open-source tooling first (vision foundation models, VLMs, point-cloud backbones, classical geometry), and know what's out there and what each is good for.

• Adapt our production models to new object classes, regions, and sensor types as customers bring them.

• Build evaluation pipelines that measure improvements and regression alike.

• Iterate on feature extraction pipelines according to customer feedback and metrics changes.

Requirements

• BS or MS in Computer Science, EE, Robotics, or a related field, or equivalent experience.

• Strong coding abilities (preferably Python + Pytorch), and comfortable working with a large codebase.

• Hands-on experience training or fine-tuning a vision model (segmentation, detection, or 3D) through work, internships, or projects.

• Working knowledge of geometry for 3D perception: coordinate systems, transforms, projecting between images and point clouds.

• Curiosity and speed: you pick up new frameworks and papers quickly and can explain what you learned to teammates.

• Clear communicator with engineers, product, and the surveyors who use what you build.

• Fluent with AI coding assistants.

Bonus qualifications

• Have used open-source vision foundation models (SAM family, DINO, Grounding DINO, or similar) in a task before.

• Experience with point clouds or LiDAR data (Open3D, PDAL, PyTorch3D, sparse convolution libraries).

• Experience deploying models to production: ONNX or TensorRT, batch inference on cloud GPUs.