Senior Machine Learning Engineer

Orchard; San Francisco (CA); On-site; USD 180,000 - 240,000; Full time

Benefits offered by this job

Equity compensation

In-office SF

Flexible hours

Health coverage

Impact-driven work

Job summary

Orchard Robotics, a San Francisco-based AI for agriculture startup, is seeking a Senior Machine Learning Engineer to design and scale ML/CV pipelines for training on billions of farm images. You will build end-to-end data processes, deploy cloud and edge training, and collaborate with agronomists to translate domain knowledge into actionable ML features.

The role offers generous equity, full-time SF office work, flexible hours, and comprehensive health coverage.

Qualifications

• 5+ years of experience building production-grade data pipelines and ML infrastructure.
• Proficiency in Python and experience with ML frameworks (TensorFlow, PyTorch).
• Strong experience with data engineering tools (Pandas, SQL, Airflow, Spark).
• Familiarity with cloud platforms (AWS, GCP, Azure) and containerization (Docker, Kubernetes).
• Experience with massive real-world training data and MLops for consistent deployment.
• Able to work independently in a fast-moving, dynamic environment with a growth mindset.
• Willingness to take on multiple roles as the company expands.

Responsibilities

• Build and maintain scalable ETL pipelines for processing large image datasets.
• Stay current with CV/ML literature and apply relevant advancements.
• Develop, deploy, and monitor infrastructure for model training, evaluation, and inference.
• Design active data-sampling to optimize collection and improve model performance.
• Collaborate across teams to integrate ML into production robotics systems.
• Work with agronomists and farmers to translate domain knowledge into ML features.
• Generalist support across the software stack as needed.

Skills

Data pipelines

Python

TensorFlow

PyTorch

Apache Airflow

SQL

Spark

Docker

Kubernetes

MLops

Tools

Pandas

Docker

Kubernetes

Job description

Orchard Robotics is a Series A startup backed by top VCs like Quiet Capital, Shine Capital, and General Catalyst. We're securing America’s food supply by building the AI farmer that automates our nation’s farms. We've raised over $25M in pursuit of our mission to help farmers farm more profitably and sustainably than ever before.

What We Do:

We start by collecting the most valuable data for farmers, telling them everything about what is growing on their millions of trees, across thousands of acres of farmland. We do this using advanced camera systems we build, that take pictures of every one of the billions of fruit in a farm. This data lives in our cloud data platform, FruitScope, that we've developed from the ground up to help farmers manage their crops with precision.

Farmers across the nation use our industry-leading software to look at their data, make critical decisions, and command farming operations on a daily basis. Our technology is used today across some of the largest farms in the nation.

The Role:

In order to analyze billions of fruit on farms all year long, our advanced, tractor-mounted camera systems have to know a.) precisely where they are, and b.) everything about the fruit they are seeing.

We are looking for a Senior Machine Learning Engineer to build creative, practical, and robust solutions to ML/CV software and infrastructure problems, relating to training edge ML models on massive amounts of real-world farm image data collected by our camera systems.

About the role:

• As an early engineer, you'll receive generous equity compensation

• Full-time role at our San Francisco, CA office

• Flexible working hours

• Comprehensive Health, Vision, and Dental coverage, and we cover 100% of the premium

• We move fast, and sometimes this means staying late or working weekends

• Our team is close-knit & highly driven, you’ll work directly with our CEO and entire team

• We’re deeply motivated by the impact we’re making – every line of code written or new system built means less food that goes to waste, and more people who are fed.

What you’ll do:

• Build and maintain scalable ETL pipelines for processing large, diverse image datasets collected from our tractor-mounted camera systems in farms.

• Stay up-to-date with current literature in computer vision models and architectures, and apply relevant advancements to our systems.

• Develop, deploy, and monitor infrastructure for model training, evaluation, and inference, both in the cloud and on edge devices.

• Design and implement intelligent active sampling infrastructure to optimize data collection and improve model performance.

• Collaborate with a multidisciplinary team to integrate ML solutions into production robotics systems.

• Work closely with agronomists and farmers to understand crop biology and translate domain knowledge into actionable ML features.

• Be a generalist, supporting different parts of our software stack as needed.

What makes you a good fit:

• 5+ years of experience building production-grade data pipelines and ML infrastructure.

• Proficiency in Python and experience with ML frameworks (e.g., TensorFlow, PyTorch).

• Strong experience with data engineering tools (e.g., Pandas, SQL, Apache Airflow, Spark).

• Familiarity with cloud platforms (AWS, GCP, or Azure) and containerization (Docker, Kubernetes).

• Experience working with massive amounts of real-world training data.

• Familiarity with MLops software and data engineering to ensure consistent deployment of ML models.

• Ability to work independently, learn quickly, and operate in a dynamic environment

• Enthusiasm for taking on multiple roles and responsibilities as our company grows.

Bonus Points:

• Experience deploying & optimizing ML models to run fast on embedded compute like NVIDIA Jetson

• Experience prototyping, evaluating, or deploying new ML/CV models on the edge.

If you're looking to help make a positive impact in the world by building the future of farming, come join us!