Member of Technical Staff (Open Role)

Adaptive ML is a frontier AI startup building a Reinforcement Learning Operations (RLOps) platform that enables enterprises to specialize and deploy LLMs into production. The Member of Technical Staff will contribute to building foundational technology, focusing on high-performance software engineering and large-scale RL research, while also engaging in systematic empirical research to drive the product roadmap.

Responsibilities:

• Develop robust software in Rust, interfacing between easy-to-use Python recipes and high-performance, distributed training code running on hundreds of GPUs
• Profile and iterate GPU inference kernels in Triton or CUDA, identifying memory bottlenecks and optimizing latency—and decide how to adequately benchmark an inference service
• Develop and execute an experiment analyzing nuances between DPO and PPO in a fair and systematic way
• Build data pipelines to support reinforcement learning from noisy and diverse user' interactions across varied tasks
• Experiment with new ways to combine adapters and steer the behavior of language models
• Build hardware correctness tests to identify and isolate faulty GPUs at scale
• Build the foundational technology powering Adaptive, with a focus on high-performance software engineering and large-scale RL research
• Contribute to our product roadmap, by identifying promising trends and high-impact findings
• Report clearly on your work to a distributed collaborative team, with a bias for asynchronous written communication
• Write high-quality software in Rust, with a focus on performance and robustness
• Profile dedicated GPU kernels in CUDA or Triton, optimizing across latency/compute-bound regimes for complex workloads
• Identify and resolve bugs in large distributed systems, at the intersection of software and hardware correctness
• Conduct research on large language models or diffusion models, systematically exploring how reinforcement learning can be used to personalize models
• Reproduce results from the RL, LLM, and diffusion literature, distinguishing the noise from the groundbreaking
• Own a research agenda, with a bias for at-scale, systematic empirical research