Senior ML Engineer, Computer Vision

Anduril; Irvine (CA); On-site; USD 220,000 - 292,000; Full time

Job summary

Anduril Industries, a defense technology company in Irvine, CA, is seeking a Machine Learning Engineer to own the full ML stack for the Counter Intrusion team. You will design and train multi-sensor object detection models for edge devices and develop learning algorithms to optimize autonomous systems.

You will implement end-to-end ML infrastructure, data collection, and training, with impact on cutting-edge defense tech and opportunities to apply novel ML across products.

Qualifications

• MS or PhD in Machine Learning, Robotics, or Computer Science with CV emphasis.
• BS in CS, ML, EE, or related field.
• 6+ years with ML algorithms on large datasets.
• Strong Deep Learning and CV background.
• Proficiency in C++ in a Linux environment.
• Experience with PyTorch, JAX, TensorFlow.
• Experience deploying models with TensorRT and ONNX.
• On-device inference optimization for CPU/GPU/NPU.
• Experience deploying CV models from R&D to production.
• Eligibility to obtain US Secret security clearance.

Responsibilities

• Propose and prototype ML solutions for defense systems.
• Develop and maintain core ML pipelines.
• Train and deploy deep learning models for real-time applications.
• Collaborate cross-functionally with camera, systems and labeling teams.
• Curate datasets for evaluating performance and comparing trends.
• Provide technical mentorship to junior ML engineers.

Skills

Machine Learning

Robotics

Computer Vision

C++

Python

PyTorch

TensorFlow

ONNX

TensorRT

Linux

CI/CD

Security clearance

Education

MS or PhD in ML/Robotics/CS

BS in CS/ML/EE or related

Tools

TensorRT

ONNX

PyTorch

JAX

TensorFlow

Linux

Job description

Anduril Industries is a defense technology company with a mission to transform U.S. and allied military capabilities with advanced technology. By bringing the expertise, technology, and business model of the 21st century’s most innovative companies to the defense industry, Anduril is changing how military systems are designed, built and sold. Anduril’s family of systems is powered by Lattice OS, an AI-powered operating system that turns thousands of data streams into a realtime, 3D command and control center. As the world enters an era of strategic competition, Anduril is committed to bringing cutting-edge autonomy, AI, computer vision, sensor fusion, and networking technology to the military in months, not years.

About the Team

The Counter Intrusion MSE team develops systems that provide force protection capabilities, monitoring the perimeter of secure areas, land or sea, for approaching people, vehicles, and vessels. We live in a world where security officers are increasingly overwhelmed by sensor data feeds. Our products leverage advanced sensor fusion and autonomy to seamlessly render activity in the environment to Lattice's common operating picture. This relieves operators of our system from a ton of burden and allows our customers to get more done with fewer personnel. Increasingly, Counter Intrusion MLEs are working on projects to bring customers' existing legacy security systems into the Lattice ecosystem. Key to this effort is building scalable software solutions so that we can service many customers without requiring bespoke software for each one. The Counter Intrusion team is responsible for the development, testing, deployment, and sustainment of our family of systems. We work closely with other teams from product, engineering, sales, logistics, operations, and mission success.

About the Role

We are looking for a Machine Learning Engineer to apply the latest research to solve our toughest problems. This role will be responsible for owning the whole machine learning stack for the Counter Intrusion team. You will design and train multi-sensor object detection models for perception on edge compute devices that push the boundaries of what's possible with our sensors. You will develop learning algorithms to optimize the behavior of autonomous systems. You will also be responsible for the end-to-end design, implementation, and performance of the ML stack, including the infrastructure for data collection and training. Your work will directly impact Anduril's ability to deliver cutting-edge defense technology, with the opportunity to identify and develop novel ML applications across our product portfolio.

Responsibilities

• Propose and prototype innovative solutions to solve real-world problems, leveraging the latest state-of-the-art techniques in the field
• Develop and maintain core ML pipelines
• Train and deploy deep learning models for real-time applications
• Collaborate cross-functionally with camera, systems and labeling teams
• Curate datasets for evaluating performance and comparing performance trends over time
• Provide technical mentorship to other junior ML engineers

Required Qualifications

• MS or PhD in Machine Learning, Robotics or Computer Science, with emphasis on Computer Vision
• BS in Computer Science, Machine Learning, Electrical Engineering, or related field
• 6+ years of experience developing, benchmarking and optimizing ML algorithms on large-scale datasets
• Strong Deep Learning and CV background
• Proficiency in C++ development in a Linux environment
• Experience with Python development and deep learning frameworks such as PyTorch, JAX and TensorFlow
• Experience deploying models with TensorRT and ONNX
• Optimize on-device inference and vision kernels across CPU/GPU/NPU
• Track record of developing and deploying CV models from R&D to production
• Experience writing and maintaining automated continuous integration tests
• Knowledge of system profiling and tuning for latency, memory and power efficiency
• Ability to conduct experiments, ablation studies and create highly detailed reports
• Eligible to obtain and maintain a U.S. Secret security clearance

Preferred Qualifications

• Experience in one or more of the following:
  • Object Detection, Object Tracking, Instance Segmentation, Semantic Segmentation, Semantic Change Detection, Depth Estimation, Model Pruning and Compression
• Experience in one or more of the following:
  • Visual Odometry, SLAM, Multi-view Geometry, Camera Models, RGB-D and LIDAR Sensor Fusion, Optical Flow
• Experience troubleshooting and analyzing remotely deployed software systems
• 1 year of experience in a technical leadership role

US Salary Range: $220,000—$292,000 USD

Benefits

At Anduril, we invest in our people. Our comprehensive, competitive benefits package (available at little to no cost to employees) ensures