Inference Optimization Engineer

Hedra; San Francisco (CA); On-site; USD 180,000 - 250,000; Full time

Benefits offered by this job

Competitive compensation and equity

401k

Healthcare (Silver PPO Medical, Vision

Dental)

Lunch and snacks at the office

Job summary

Hedra is seeking an Inference Optimization Engineer to join our San Francisco team, working at the boundary between research and systems to accelerate state-of-the-art visual models at inference time.

You'll profile models, implement optimizations across architectures, runtimes, and kernels, and collaborate with researchers and engineers to push performance while maintaining accuracy. This is a hands-on, hardware-aware role in a fast-moving ML systems group.

Qualifications

• Deep technical expertise in efficient ML inference.
• Strong understanding of how DL models execute on hardware.
• Experience profiling ML workloads and driving performance gains.
• Proficient in Python or C++ for systems work.
• Familiarity with PyTorch, CUDA, or Triton.

Responsibilities

• Work with researchers to make new visual models fast at inference time.
• Profile architectures and workloads to identify bottlenecks.
• Develop approaches to reduce latency and improve GPU utilization.
• Explore optimizations like quantization, sparsity, and kernel fusion.
• Implement GPU kernels and optimize multi-GPU/multi-node execution.
• Build benchmarking and profiling infrastructure to measure impact.

Skills

ML inference

ML systems

GPU computing

Python

C++

Performance profiling

Cross-functional collaboration

Tools

PyTorch

CUDA

Triton

TensorRT

vLLM

SGLang

Job description

About Hedra

Hedra is the platform, models, and infrastructure for visual intelligence.

About Hedra

Hedra is the platform, models, and infrastructure for visual intelligence.

We build models and systems that push the frontier of visual intelligence, along with the infrastructure required to make those models fast, efficient, reliable, and accessible at scale.

We’re a small, highly technical team in San Francisco, backed by a16z and other leading investors. Researchers and engineers at Hedra work closely across boundaries, own problems end to end, and have significant influence over both what we build and how we build it.

The Role

We’re looking for an Inference Optimization Engineer to work alongside our research team on making state-of-the-art visual models fast and efficient at inference time.

You’ll work at the boundary between research and systems, taking new model architectures and figuring out how to run them efficiently on modern hardware. That means understanding where time and memory are being spent, identifying opportunities for algorithmic and systems-level improvements, and implementing optimizations across model architecture, inference algorithms, runtimes, kernels, and distributed execution.

The problems rarely live neatly within one layer of the stack. Depending on what you find, you might modify how a model executes, develop a new inference technique, write a custom GPU kernel, rethink memory movement, or change how work is distributed across accelerators.

We care more about technical depth, curiosity, and demonstrated ability than years of experience. We’re open to experienced ML systems engineers as well as exceptional early-career engineers or researchers who have already gone unusually deep on model performance, GPU systems, or efficient inference.

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.
• Strong programming fundamentals in Python, C++, or another systems-oriented language.
• Experience with some combination of PyTorch, CUDA, Triton, TensorRT, vLLM, SGLang, or comparable technologies.
• Ability to reason across abstraction layers rather than treating model architecture, framework, runtime, kernel, and hardware boundaries as fixed.
• Strong intuition for performance tradeoffs across latency, throughput, memory, numerical precision, model quality, and complexity.
• Curiosity about how models work internally and a willingness to modify or rethink existing approaches when the performance problem calls for it.
• Comfort working on ambiguous problems where the bottleneck, and sometimes even the right question, is not known in advance.
• Ability to communicate technical ideas clearly and collaborate closely with research scientists and engineers.

Nice to Have

• Experience optimizing large generative, multimodal, vision, or video models.
• CUDA, Triton, CUTLASS, or other GPU kernel development.
• Deep knowledge of GPU architecture, memory hierarchy, and hardware-aware optimization.
• Experience with attention optimization, kernel fusion, memory-efficient execution, or custom operators.
• Model compilation or graph optimization experience.
• Quantization, sparsity, caching, speculative execution, or other efficient inference techniques.
• Experience optimizing diffusion, autoregressive, transformer, or other large generative architectures.
• Multi-GPU or multi-node model execution, including tensor, pipeline, sequence, or other forms of parallelism.
• Experience optimizing communication or data movement between accelerators.
• Experience with profiling tools such as Nsight Systems or Nsight Compute.
• Contributions to ML systems, inference runtimes, compilers, GPU libraries, or performance-focused open-source projects.
• Research or publications in efficient ML, ML systems, GPU computing, compilers, or related areas.

Benefits

• Competitive compensation and equity
• 401k
• Healthcare (Silver PPO Medical, Vision, Dental)
• Lunch and snacks at the office

This role is based in San Francisco, and we work together in person five days a week.