Join our company, an innovative startup building a fully-managed LLM-inference platform, that enables data heavy enterprises to perform any AI task at any scale without limits.
We're looking for an Experienced Performance Researcher to join our founding team. Youll be responsible for building and optimizing scalable cloud infrastructure solutions tailored for AI workloads. This role offers a unique opportunity to directly shape our infrastructure strategy, improve system reliability and performance, and contribute to establishing our company as a leader in adaptive AI compute management.
Join us to tackle the magic that make AI tick under the hood and build the backbone powering the AI revolution.
What Youll Do
- Design and build high-performance distributed inference pipelines for LLMs, focused on large-batch, non-real-time scenarios.
- Optimize GPU memory usage, kernel execution, and communication across nodes (NCCL, MPI, etc.).
- Own CUDA kernels, compiler-level tricks, and multi-GPU scheduling logic.
- Lead profiling and performance tuning for throughput, and cost- down to the kernel level.
- Collaborate with infra, product, and research teams to define SLAs, resource allocation logic, and runtime behaviors.
- Help build the core infrastructure that will run LLM workloads across hybrid GPU environments (cloud/on-prem/self-hosted).
Requirements: - Deep experience with CUDA programming, GPU architecture, and low-level performance engineering.
- Fluency with Python and C++, and a mastery of profiling tools like Nsight, nvprof, perf, etc.
- Experience building systems for large-scale distributed training or inference (PyTorch, DeepSpeed, Ray, Horovod, etc.).
- Hands-on familiarity with cluster and container orchestration tools (Kubernetes, Slurm, Docker).
- Self-motivated and able to operate independently in a fast-moving startup environment.
- Strong analytical skills and a passion for elegant performance wins.
- A collaborative team player with strong interpersonal skills, a positive and easygoing attitude, and the potential to grow into a leadership role.
- Prior experience building inference runtimes or scheduling frameworks.
- Experience with serverless GPU models, model parallelism, tensor slicing, and batching tricks.
- Contributions to open-source HPC or ML infra projects.
- Understanding of AI/ML privacy and compliance concerns in enterprise environments.
- Track record of working on distributed systems at bleeding-edge research labs or infrastructure teams.
This position is open to all candidates.