Edge AI ML Engineer - Remote, On-Device & Edge Deployments

Madrona Venture Labs; United States; Remote; USD 150,000 - 230,000; Full time

Benefits offered by this job

100% health, dental, and vision for员工

100% remote first culture; work fromUS

401K program

Unlimited PTO

IT stipend for new equipment

Job summary

EdgeRunner AI is recruiting for a role focused on building the EdgeRunner Research organization. You will contribute to data acquisition, processing, evaluation, and efficient parallelization across ML pipelines at scale.

Strong candidates will bring experience with scalable libraries, distributed training, and advanced training architectures, including distillation and RL. A remote-first culture supports work from anywhere in the US.

Qualifications

• Experience building libraries and owning codebases in scalable data processing.
• Experience with distributed model training environments.
• Familiarity with complex training architectures (distillation, RL, etc.).
• Experience with specialized reinforcement learning gyms or environments.
• Experience with compute and cluster management.
• Experience with data, model, and pipeline versioning.
• Experience with compute kernel development or quantization and compression.
• Experience with large-scale evaluations in ML systems.

Responsibilities

• Build the foundations of the EdgeRunner Research organization.
• Develop code for data acquisition, processing, evaluation, and parallelization.
• Create high-performance kernels and optimize quantization and compression pipelines.
• Contribute to scalable data processing libraries and training environments.
• Collaborate across teams to align technical solutions with business needs.

Skills

Data processing

Distributed training

Training architectures

RL environments

Compute cluster mgmt

Versioning

Quantization

Large-scale evaluations

Job description

EdgeRunner AI is recruiting for a role focused on building the EdgeRunner Research organization. You will contribute to data acquisition, processing, evaluation, and efficient parallelization across ML pipelines at scale.

Strong candidates will bring experience with scalable libraries, distributed training, and advanced training architectures, including distillation and RL. A remote-first culture supports work from anywhere in the US.