Core Engineering

About the role

We are hiring a Core Engineer to help design and operate the foundational infrastructure behind Rox’s autonomous agent platform. This role is ideal for engineers who have deep systems intuition and want to work on infrastructure problems at the frontier of AI reliability.

Core Engineering Team

The Core Engineering Team builds the systems that make autonomous revenue agents reliable at enterprise scale. This team sits at the center of Rox’s long-term technical strategy and owns foundational infrastructure across:

• agent reliability and orchestration
• distributed execution systems
• graph-based retrieval infrastructure
• streaming and real-time context systems
• observability for autonomous workflow
• slow-latency data and inference pipelines

What You’ll Do

• Build infrastructure for reliable autonomous agent execution
• Design systems for deterministic, auditable agent behavior at enterprise SLAs
• Develop low-latency retrieval and context systems powering AI workflows
• Build and scale graph-based infrastructure and semantic retrieval systems
• Improve observability, debugging, and reliability across distributed agent systems
• Work on real-time data ingestion and streaming architectures
• Collaborate closely with platform, AI, and product engineering teams
• Help shape the long-term architecture behind Rox’s agent runtime

Problems You’ll Work On

• Reliability for long-horizon AI workflows
• Agent orchestration across distributed systems
• Deterministic execution for autonomous systems
• Streaming context ingestion and retrieval
• Knowledge graph infrastructure
• Real-time state synchronization
• Low-latency execution pipelines
• Enterprise-grade observability for agent systems

Must-Have Qualifications

• Strong background in distributed systems or platform engineering
• Experience building and operating high-scale backend infrastructure
• Strong systems fundamentals across networking, concurrency, storage, and reliability
• Experience with streaming systems, distributed databases, or real-time infrastructure
• Able to independently design and ship complex technical systems
• Strong product and engineering judgment

Possibly Relevant Backgrounds

• Apache Flink
• distributed query engines
• real-time OLAP systems
• graph retrieval systems
• semantic search infrastructure
• streaming compute systems
• large-scale platform engineering
• AI infrastructure and orchestration systems

Why This Role Exists

Enterprise AI systems are moving toward autonomous execution. The hard problem is not generating outputs — it's building reliable systems that can reason, retrieve context, coordinate actions, and operate deterministically under real-world enterprise constraints. We believe this requires a new category of infrastructure engineering. That is the problem space this team exists to solve.

Location

This role is based onsite in San Francisco. We strongly believe that the speed and complexity of the problems we are solving benefit from in-person collaboration. We actively relocate exceptional engineers from around the world and currently have team members who have moved from Europe, Canada, Asia, and Australia to join Rox.