Research Scientist – Geo-Distributed Inference

This is a fully remote position, open to applicants in United States, +2 more locations.

📋 Description

• Develop and manage the complete inference stack from start to finish

• Establish the strategy for pipeline-parallel execution, placement and routing, transportation, serving engine, and failure management

• Create, design, validate, and implement algorithms for rapid inference on consumer hardware over the public internet

• Maintain a fast and reliable rollout pipeline for reinforcement learning training

• Build the serving layer for models once they have been trained

• Facilitate inference across Macs and consumer GPUs utilized by distributed participants

• Manage nodes that join and leave during execution and adapt to changes in model weights during training

⛳️ Requirements

• Proven experience in delivering serving-engine internals or constructing a large-scale inference system

• Practical expertise in working on serving systems

• Publications in distributed inference or related fields, such as LLM serving systems, pipeline parallelism over slow networks, or decentralized training, or equivalent unpublished work that can be elaborated upon

• Background in low-bandwidth, high-latency systems functioning over the public internet

• Conviction in Protocol Learning as a feasible approach for collective, trustless, and sovereign AI

• Familiarity with reinforcement learning post-training

• Exposure to Apple silicon or MLX technology

• Experience with peer-to-peer networking and NAT traversal

• Background in proprietary, open-weight, or open-source AI research labs

• Proficient in English, both written and spoken, at a professional level

• Capability to collaborate across different time zones

🏝️ Benefits

• Substantial equity ownership for key technical contributors along with a competitive base salary

• Flexible working environment

• Optional full visa sponsorship available

• Relocation assistance to Australia or the US

• Opportunity to engage in open, cutting-edge research challenges

• Remote-first organizational culture

• Team members located globally