Staff Ops Engineer

We're looking for founding team members of 'Anterior Labs', our applied research arm where "applied" means "shipped". We ship research to benefit users. We need exceptional staff level research engineers who can perform LLM inference accurately at scale. You'll work with infrastructure experts to deploy models into production.

About the role:

• Lead, design, and implement architecture for hosting LLM-based systems
• Optimize logical reasoning systems for speed, scale, and cost
• Improve LLM-based system performance, including fine-tuning and creating efficient agent networks
• Collaborate with product and clinical teams for rapid prototyping

About you:

• Extensive Python/Golang/Rust programming experience
• Expertise in machine learning and GPU-based compute architectures
• Experience with LLMs (OAI, Anthropic, Mistral) and SLMs (Llama, Phi)
• Experience with distributed data processing and large-scale system architecture
• Problem-solving and communication skills
• High agency and curiosity

Preferred:

• Experience working with research teams to enhance search quality
• Track record of building large-scale knowledge bases
• Experience deploying ML models over 70B parameters or multi-GPU systems

Benefits:

• Default in-person culture with flexibility
• Health and dental benefits
• Flexible holiday policy
• Free office lunch daily
• Commute coverage
• Customizable work environment