Senior Machine Learning Engineer

Andromeda builds personalised robot companions for the elderly. We are pioneering the future of human-robot interaction where no playbook exists. We are backed by investors including San Francisco-based Forerunner Ventures, Rethink Impact and Main Sequence Ventures. We're working towards robots that feel genuinely alive - think Disney-level emotional connection. We have real customers, real end-users and have the runway to investigate and demonstrate technical breakthroughs.

As a Senior Machine Learning Engineer focused on Computer Vision (CV), you'll build production CV systems that enable our robots to understand and respond to human behaviour. You'll develop capabilities for person identification, emotion recognition, and scene understanding that make interactions feel natural and empathetic. You'll work across the full stack: from model development to deployment on edge devices and cloud infrastructure, integration with our conversational AI system, to monitoring, observability and continuous improvement. You’ll help establish our CV practices.

We follow a rapid iteration approach: leverage open source foundations, extend with novel research, and build proprietary breakthroughs. You'll have significant autonomy to shape our computer vision capabilities and help define our ML culture as we build the team from the ground up.

This role focuses on production engineering. If you're primarily interested in novel algorithm development, please see our separate Applied Research role.

Your first year:

- Months 0-6: Onboard and mature existing computer vision features, collecting data, optimising performance, improve testing and observability
- Months 6-12: Productionise and deploy new CV capabilities to enhance how Abi perceives and responds to users
- Months 12+: Contribute to the feature roadmap, architect new perception systems, establish robust product feedback loops with cross-functional teams

Responsibilities

- Architect and deploy computer vision systems for human understanding (person identification, emotion recognition, scene understanding)
- Build production pipelines for real-time visual perception on hybrid edge/cloud architecture
- Develop robust inference systems optimised for edge deployment (NVIDIA Jetson) and cloud processing
- Integrate computer vision outputs with conversational AI and other robot systems
- Design and implement testing infrastructure, simulation environments, and observability tools for CV systems
- Collaborate with teams to productionise computer vision prototypes for real-world deployment
- Establish Machine Learning (MLOps) practices, monitoring, and continuous improvement processes for CV models in production
- Work closely with product, engineering, robotics, and customer success teams to understand user needs and build product feedback loops
- Mentor team members and set technical standards for computer vision engineering
- Drive technical decision-making for ambiguous, high-impact problems in human perception
- Write clean, maintainable and well-documented code

About You

- You're excited about applying computer vision to robotics and human-robot interaction, particularly creating meaningful experiences for elderly users
- You've architected and shipped production computer vision systems at scale
- You've been at the sharp end of hard technical problems in CV - whether it's real-time perception, edge deployment, or challenging lighting/environmental conditions
- You thrive in 0-to-1 environments where you're building the playbook
- You've been through multiple product cycles and understand what it takes to ship CV systems to real users
- Committed to continuous learning and staying current with best practices in computer vision and deep learning
- Able to work both autonomously and collaboratively with excellent communication skills
- You have strong technical leadership skills and enjoy mentoring engineers

Requirements

- Bachelor's, Master's or PhD in Computer Science, Robotics, Computer Vision, Engineering, or related field
- 5+ years of professional experience building production computer vision systems
- Deep expertise in computer vision for human understanding (person identification, emotion recognition, scene understanding)
- Strong fundamentals in computer vision, deep learning, and mathematics (linear algebra, probability, optimisation)
- Proficiency in Python and modern ML frameworks (PyTorch, TensorFlow, or similar)
- Experience deploying CV models to production with real-time video processing and inference optimisation
- Proven track record architecting and shipping complex ML systems end-to-end
- Strong software engineering practices (testing, version control, code review, documentation)
- Experience with MLOps, model monitoring, and production debugging
- Demonstrated ability to take ownership of ambiguous problems and drive them to completion
- Melbourne-based role requiring five days on-site

Preferred Experience

- Edge ML deployment experience (NVIDIA Jetson)
- AWS cloud infrastructure for testing computer vision pipelines
- Experience with multimodal systems (combining vision with conversational AI or other modalities)
- Video understanding, temporal modelling, or action recognition
- 3D computer vision, depth sensing, or sensor fusion
- Human-centred computer vision in challenging real-world conditions (varying lighting, occlusions, diverse user populations)
- Experience in high-reliability environments (consumer robotics, automotive, healthcare, assistive technology)
- Working in early-stage or fast-scaling environments
- Experience building CV systems for elderly or accessibility applications

#J-18808-Ljbffr