Morph Hires Performance Engineer to Boost Inference Infrastructure
Morph, a company building inference infrastructure for fast open models, has hired a performance engineer to optimize its system for speed, cost, and reliability. The engineer will work with founders to identify bottlenecks and implement fixes, with a focus on GPU performance and model quality.
Key points
- Morph, a startup from Y Combinator's S23 batch, is hiring a performance engineer to improve its inference infrastructure.
- The engineer will work on optimizing the system's performance, focusing on GPU performance, memory bandwidth, and inference serving.
- The role requires expertise in Python, GPU performance, and memory bandwidth, as well as experience with complex production systems.
- The performance engineer will work directly with the founders to identify and fix bottlenecks, with a focus on model quality and correctness.
- The position offers immediate production impact and the opportunity to work on frontier-scale models.
Morph, a startup from Y Combinator's S23 batch, is hiring a performance engineer to improve its inference infrastructure. The company builds the infrastructure behind the fastest open models, and the performance engineer will play a crucial role in optimizing its system for speed, cost, and reliability.
The performance engineer will work on a wide range of tasks, including tracing latency and throughput regressions, optimizing batching and scheduling, and building benchmarks and observability. They will also be responsible for validating that every optimization preserves model quality and correctness.
The role requires expertise in Python, GPU performance, and memory bandwidth, as well as experience with complex production systems. The performance engineer will work directly with the founders to identify and fix bottlenecks, with a focus on model quality and correctness.
The position offers immediate production impact and the opportunity to work on frontier-scale models. For the right candidate, this could be a unique chance to make a significant contribution to the field of artificial intelligence and machine learning.
Sources
The WireByte editorial team synthesises technology news from multiple primary sources, verifies the facts, and links every source. Articles are produced with AI assistance and reviewed under our editorial policy.