Remote Geo-Distributed Inference Architect

OpenKrill; United States; Remoto; USD 180.000 - 240.000; Tempo pieno

Vantaggi offerti da questo lavoro

Equity-Heavy Package

Remote-First Culture

Visa Sponsorship

Open Problems

Descrizione del lavoro

Pluralis Research seeks engineers to build and maintain the end-to-end inference stack for decentralized RL training and serving on consumer hardware over the public internet.

You will ship fast, robust systems, invent new algorithms, and ensure rollout pipelines for RL and serving. The role emphasizes working across time zones with a remote-first culture and equity-based compensation.

Competenze

• Shipped serving-engine internals or built a large-scale inference system.
• Publications (papers/blogs) in distributed inference or LLM serving are a plus.
• Experience with low-bandwidth, high-latency networks.
• Belief in Protocol Learning as a viable path for sovereign AI.

Mansioni

• Own the inference stack end-to-end: parallel execution, placement, routing, transport, serving engine, and failure handling.
• Invent algorithms to accelerate inference on consumer hardware over the internet and validate them for production.
• Keep rollout pipelines fast and reliable for RL training and serving.

Conoscenze

Shipped serving systems

Research ability

Low-bandwidth networking

Mission alignment

Descrizione del lavoro

Pluralis Research seeks engineers to build and maintain the end-to-end inference stack for decentralized RL training and serving on consumer hardware over the public internet.

You will ship fast, robust systems, invent new algorithms, and ensure rollout pipelines for RL and serving. The role emphasizes working across time zones with a remote-first culture and equity-based compensation.