MorphLLM is building Fast Apply models - get changes from Claude/Gemini into your code FAST

Morph builds the fastest LLM code editing engine on the market — speculative decoding, and more. Our stack powers high-throughput AI workflows for vibe coding apps, devtools, PR bots, and IDEs.

We're hiring a founding engineer to push the limits of performance, safety, and scalability across our inference, retrieval, and diffing pipelines.

What You’ll Do

• Build fast, reliable systems to apply LLM-generated edits.
• Have used an ML framework like Pytorch, Tensorflow, or JAX in projects or at work
• Work across low-latency inference, containerized deployment, and CI/CD tooling
• Work with kernels and bleeding edge inference research.
• Implement the latest research into production quality systems

You’re a Fit If You

• Ship fast in TypeScript, Python, and others.
• Know your way around real infra: Docker, Kubernetes, Linux, observability
• Have experience with LLM apps, devtools, compilers, building games, or code intelligence
• Strong understanding of Pytorch/TF/JAX
• Prior experience with low level inference optimizations (ex. kernels)
• Prefer ownership and agency > bureaucracy

Why Morph

• zero fluff - work directly with the founder. Everyone on the team is an ML engineer
• We will never make you do story points
• Work on the fastest model in the world - 2.3x the speed of the fastest cerebras model

Nvidia, CUDA, FastAPI