Software Engineer, Compiler (AX Engineer)
About FuriosaAI
FuriosaAI builds high-performance, high-efficiency AI compute for the Inference Era. Founded in 2017 by veteran semiconductor and AI algorithm engineers, Furiosa operates globally with offices in Korea and Silicon Valley, along with a compiler-focused R&D lab in Lisbon.
Our vision is to make AI computing sustainable, enabling access to powerful AI for everyone on Earth. We solve the AI hardware energy and operational cost crisis at the architectural level, rather than through brute force, building the world's first truly AI-native compute platform to unlock the full potential of artificial intelligence for every enterprise.
About the Role
The Compiler team at FuriosaAI builds the software stack that enables ML models to run at peak performance on our AI accelerator hardware. This is a newly established role - there's no playbook yet. You'll be the first person to define and operationalize AI-assisted engineering workflows for the team: identifying high-leverage bottlenecks, running experiments, and shipping repeatable tooling + playbooks that stick. While you’ll be embedded in the Compiler team, compiler specialization is not required - your scope can span development, code review, debugging, CI/testing, documentation, and project execution.
If you're the kind of engineer who gets uncomfortable without a clear job description - this role isn't for you. If you're the kind who sees an undefined space and immediately starts mapping it - read on.
Key Responsibilities
Identify pain points and leverage opportunities across the engineering workflow (development, code review, debugging, CI/testing, documentation, and project execution)
Research, prototype, and benchmark AI/automation tools (e.g., coding agents, LLM-assisted review, debugging assistants) against real team workflows
Design and maintain team-specific prompt libraries, workflow templates, and integration guides (IDE, code review, CI, debugging, documentation)
Improve CI/testing signal quality and feedback loops (e.g., flaky test reduction, failure triage workflows)
Lead onboarding sessions, regular Q&A sessions, and internal knowledge sharing for newly adopted tools
Define and track adoption + impact metrics (e.g., PR cycle time, review turnaround, time-to-triage regressions, CI flakiness), and iterate based on data and feedback
Monitor the AI tooling ecosystem and surface relevant developments to the team
Minimum Qualifications
3+ years of software engineering experience
Hands-on experience with LLM-based coding tools (e.g., GitHub Copilot, Cursor, Claude Code, Codex, or equivalent)
Strong understanding of software development workflows from the perspective of a practicing engineer
Ability to rapidly evaluate new tools and translate findings into actionable team guidance
Preferred Qualifications
Background in compiler engineering, systems programming, or static analysis
Experience building or customizing LLM-based agents or tooling via API
Track record of driving internal tooling adoption or developer experience improvements
Experience producing technical documentation, runbooks, or internal tech talks
Experience improving engineering workflows (DevOps, CI/CD, developer productivity, or technical program execution)