Inference Optimization Engineer

About the role

ABOUT HEDRA

Hedra is a research and infrastructure lab advancing post-training and inference for multimodal and physical AI. Our ambition is to bring recursive self-improvement to models that learn from and interact with the real world.

We combine reinforcement learning research with GPU compute and optimized inference to help teams post-train, serve and continuously improve models they own.

We're backed by Index Ventures, a16z and Abstract Ventures. Our team works fully in person in San Francisco.

We're looking for people with startup experience who take ownership of their work and care deeply about the problems our customers need to solve. You'll help build the technology, products and business that turn this research into a lasting company.

WHAT YOU’LL DO

- Work directly with research scientists and engineers to make new visual models fast and efficient at inference time.

- Profile model architectures and workloads to understand bottlenecks across compute, memory, communication, and model execution.

- Develop and implement new approaches to improving inference latency, throughput, memory efficiency, and GPU utilization.

- Explore algorithmic optimizations including quantization, sparsity, caching, compilation, attention optimizations, and alternative execution strategies.

- Build or optimize GPU kernels using CUDA, Triton, or similar technologies when existing implementations leave performance on the table.

- Optimize model execution across single-GPU, multi-GPU, and multi-node environments.

- Reason about the interaction between model architecture and hardware, and work with researchers when architectural changes can unlock meaningful performance improvements.

- Investigate communication, memory movement, parallelism, and distributed execution strategies for large visual models.

- Build rigorous benchmarking, profiling, and performance-regression infrastructure to understand performance and evaluate new optimization ideas.

- Evaluate new inference runtimes, compilers, frameworks, optimization techniques, and accelerator hardware.

- Stay close to advances in efficient inference, GPU programming, model architectures, compilers, and ML systems research, and rapidly test promising ideas.

- Help turn research breakthroughs into models that can be deployed and served efficiently at scale.

WHAT WE’RE LOOKING FOR

- Deep technical ability in efficient ML inference, ML systems, GPU computing, or adjacent research, demonstrated through research, production engineering, open-source contributions, or unusually ambitious independent work.

- Strong understanding of how modern deep learning models execute on hardware, including the relationship between compute, memory, communication, and performance.

- Experience profiling ML workloads, identifying bottlenecks, forming hypotheses, and driving measurable performance improvements.