Autonomy ML Engineer: Vision & Robotics

Tycho.AI, Inc.; Cambridge (MA); On-site; USD 140,000 - 190,000; Full time

Benefits offered by this job

Competitive salary

Equity

Generous benefits package

Job summary

Tycho.AI is redefining autonomous intelligence and seeking an ML/embedded engineer to design and optimize models for computer vision and robotics. You’ll build and refine training pipelines, compress and deploy models for edge devices, and tune on-device inference for latency and accuracy.

The role emphasizes strong coding in Python/C++, experience with PyTorch/TensorFlow, and collaboration within a fast-growing startup environment focused on national security and commercial AI applications.

Qualifications

• Bachelor’s or advanced degree in CS/Engineering.
• Hands-on experience applying ML to computer vision and robotics.
• Proficiency with PyTorch or TensorFlow.
• Strong coding skills in Python or C++.
• Experience deploying ML models and building training pipelines.

Responsibilities

• Design and optimize ML models for computer vision and robotics under tight compute and memory budgets.
• Build robust training and fine-tuning pipelines for large-scale datasets.
• Compress, accelerate, and deploy models (quantization, distillation) for embedded accelerators (NPU/TPU/GPU delegates).
• Profile and tune on-device inference pipelines for latency, throughput, and accuracy.
• Write clean, efficient, and maintainable code across Python and/or C++.
• Stay current on state-of-the-art ML techniques and efficient edge deployment research in autonomy and perception

Skills

ML model design

Python/C++

PyTorch/TensorFlow

Computer vision/robotics

On-device deployment

Git

Education

Bachelor’s or higher in CS/Engineering

Tools

PyTorch

TensorFlow

ONNX

ROS2

CUDA

Job description

Tycho.AI is redefining autonomous intelligence and seeking an ML/embedded engineer to design and optimize models for computer vision and robotics. You’ll build and refine training pipelines, compress and deploy models for edge devices, and tune on-device inference for latency and accuracy.

The role emphasizes strong coding in Python/C++, experience with PyTorch/TensorFlow, and collaboration within a fast-growing startup environment focused on national security and commercial AI applications.