On-Device ML Engineer: Edge Systems & Performance

Base Compute; Melbourne; Hybrid; AUD 120,000 - 180,000; Full time

Benefits offered by this job

Equity

Strong base salary

Direct influence

Low bureaucracy

Job summary

Base Compute seeks an ML Engineer to push on-device AI from research to production. You will own the inference stack and influence technical bets, working across silicon-level optimization and distributed systems.

Ideal candidates have 3+ years in ML engineering or systems programming, strong GPU/HW optimization skills, and a proactive, owning mindset with clear communication. Melbourne-Berlin based, in-person collaboration expected.

Qualifications

• 3+ years in ML engineering or systems programming.
• Experience with GPU programming and hardware optimization.
• Strong ownership and ability to translate research into production.
• Excellent written and spoken English.

Responsibilities

• Develop and scale our on-device inference engine and runtime.
• Perform cross-platform silicon optimization across architectures.
• Build robust, low-latency serving runtimes in C++.
• Profile performance and remove bottlenecks across the stack.

Skills

ML engineering

Systems programming

GPU programming

Ownership and autonomy

Communication

Tools

CUDA

ROCm

Metal

Triton

Job description

Base Compute seeks an ML Engineer to push on-device AI from research to production. You will own the inference stack and influence technical bets, working across silicon-level optimization and distributed systems.

Ideal candidates have 3+ years in ML engineering or systems programming, strong GPU/HW optimization skills, and a proactive, owning mindset with clear communication. Melbourne-Berlin based, in-person collaboration expected.