Senior ML Engineer Perception R&D

Senior Machine Learning Engineer – Robotic Perception

About the Role

A fast-growing robotics company is seeking a Senior Machine Learning Engineer to help advance the next generation of AI-driven robotic perception systems used in large-scale logistics environments.

This role focuses on applying foundation models, vision-language models (VLMs), and generative AI techniques to solve complex perception challenges that arise in real-world robotic deployments. The work centers on addressing the “long tail” of edge cases—situations that traditional perception systems struggle with—while helping translate cutting-edge research into robust, production-ready systems.

You will operate at the intersection of advanced research and real-world robotics, contributing to both algorithm development and the deployment of scalable machine learning solutions.

Key Responsibilities

Address Rare and Edge-Case Events
Design and implement strategies to detect and manage uncommon or unpredictable scenarios such as irregular packaging, damaged items, occlusions, or challenging visual conditions.

Leverage Foundation Models
Adapt and fine-tune large-scale foundation models and vision-language architectures for robotic perception and manipulation tasks, enabling improved generalization and adaptability.

Optimize Models for Edge Deployment
Transform large, computationally intensive models into efficient, low-latency solutions suitable for deployment on edge compute platforms.

Translate Research Into Production
Evaluate emerging research in computer vision and machine learning, translating relevant innovations into reliable production systems.

Technical Leadership
Provide technical guidance, contribute to architectural decisions, and mentor engineers within the team.

Requirements

5+ years of experience in computer vision, deep learning, or machine learning with an emphasis on applied research or advanced R&D.

Hands-on experience with modern ML architectures such as Vision Transformers (ViT), Self-Supervised Learning (SSL), Vision-Language Models (VLMs), or zero-shot detection approaches.

Strong programming skills in Python with deep experience using PyTorch.

Experience solving complex perception challenges such as occlusions, reflective materials, and variable lighting conditions.

Experience with model optimization techniques including distillation and quantization.

Ability to communicate complex ML concepts and research insights to cross-functional engineering and product teams.

Familiarity with containerized environments and cloud infrastructure such as Docker and AWS or GCP, along with experiment tracking tools.