---
title: 'Inference Optimization Engineer at Hedra'
canonical: 'https://feeny.ai/job/inference-optimization-engineer-hedra-san-francisco-jn57nvy53h46'
type: 'job'
last_seen: '2026-10-17'
---

# Inference Optimization Engineer at Hedra

- **Company:** Hedra
- **Location:** San Francisco, CA
- **Employment:** full-time
- **Posted:** 2026-10-08
- **Last confirmed live:** 2026-10-17
- **Apply:** https://jobs.ashbyhq.com/hedra/f28645f7-2bed-4754-9da2-a3aaa7d6aa27

## Job description

## 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.

We don’t expect every candidate to have experience across the entire stack. Exceptional depth in one or more relevant areas, combined with the ability and curiosity to reason across the others, matters more to us than checking every box.

## 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.

## About Hedra

## Company Overview
- **One-liner**: Hedra is a Frontier AI Lab building a unified creative superintelligence platform that enables content creators and marketers to generate video, image, and audio content using proprietary and partner AI models.
- **Entity Type**: Private (Series A)
- **Headquarters**: San Francisco, California, United States (also has an office in New York)
- **Founded**: 2023
- **Founders**: Not publicly named; the founding team is listed as part of the core leadership.

## Core Business
- **Primary industry/industries**: Generative AI (GenAI), Creative Software, Video Production, Marketing Technology
- **Target customers**: B2B (content creators, marketers, businesses of all sizes); B2C (individual creators). Over 125k businesses use the platform.
- **Mission or purpose statement**: "Help build the future of generative media" and "usher in a new era of visual-first storytelling, where every creator can create stunning content at scale." [hedra.com](https://www.hedra.com/company)

## Products & Services
- **Hedra Agent**: A creative agent that learns a user’s brand, connects to their data, searches the web, and creates reusable skills. It can strategize, ideate, plan, and execute creative work.
- **Character-3 (Proprietary Model)**: Hedra’s category-leading audio-to-video multimodal foundation model for video generation, enabling realistic character animation and lip-sync.
- **Character-1.5**: An earlier version of their video generation model.
- **Infinite Canvas**: A workspace where users can generate videos using Hedra’s proprietary models or other leading generative AI models.
- **All-the-Models Platform**: Provides access to top models across video, image, and audio categories, with an agent that intelligently selects the right model for each task.

## Market Standing
- **Valuation/Market Cap**: Not disclosed
- **Key Metric**: **Total Funding**: $43M (as of latest reports) [linkedin.com](https://www.linkedin.com/company/hedra-labs)
- **Notable Investors/Partners**: Andreessen Horowitz (a16z), Index Ventures, Abstract Ventures, Alexa Fund, AWS Generative AI Accelerator. [cbinsights.com](https://www.cbinsights.com/company/hedra)
- **Growth Signals**:
    - Used by over 125,000 businesses.
    - Headcount grew +108.7% year-over-year (reaching ~44 employees).
    - Raised $32M in a Series A round led by Andreessen Horowitz in May 2025. [linkedin.com](https://www.linkedin.com/company/hedra-labs)
    - Received $1M in non-equity assistance from Amazon Web Services in November 2025. [linkedin.com](https://www.linkedin.com/company/hedra-labs)
    - Billions of impressions generated by their models. [linkedin.com](https://www.linkedin.com/company/hedra-labs)

## Competitive Advantages
- **Unified Creative Superintelligence**: Combines a proprietary agent, top-tier models (including their own Character-3), and an infinite canvas into a single workflow, competing with fragmented tools.
- **Category-Leading Video Model**: Their audio-to-video multimodal foundation model (Character-3) is a key differentiator in the generative video space.
- **Brand Learning**: The platform learns from every asset a user creates, building deep brand intelligence that accelerates workflow and ensures output alignment over time.
- **Strong Funding & Backing**: Backed by top-tier VCs (a16z, Index Ventures) and strategic partners (AWS, Alexa Fund), providing resources for rapid scaling.

## Strategic Focus
- **Scaling the Agent**: Developing the "Hedra Agent" to be the central hub for creative work, capable of researching, reasoning, and producing content.
- **Multi-Model Platform**: Continuing to integrate the best models across video, image, and audio, rather than relying solely on a single proprietary model.
- **Enterprise Readiness**: Targeting large businesses with features like brand intelligence, reusable skills, and data connectivity.
- **International Growth**: Operating in 11 countries and actively hiring to support global expansion. [linkedin.com](https://www.linkedin.com/company/hedra-labs)

## Why Work Here
- **High-Impact Work**: Join a small, fast-growing team (~44 people) building frontier AI models and products that are already used by hundreds of thousands of businesses.
- **Culture & Values**: Emphasizes ownership, action, hands-on leadership, customer obsession, empathy, respect, and unity. Described as a meritocracy where ideas are valued regardless of title. [hedra.com](https://www.hedra.com/company)
- **Cutting-Edge Tech**: Work on the latest in generative AI (video, image, audio) with a team that includes talent from Meta, HeyGen, Synthesia, and other top AI labs. [linkedin.com](https://www.linkedin.com/company/hedra-labs)
- **Locations**: Offices in San Francisco and New York. Remote/hybrid policy is not explicitly stated, but the presence of multiple offices and a globally distributed team suggests flexibility.
- **Active Hiring**: Currently hiring for multiple high-impact roles including Research Scientist, Senior Full-Stack Engineer, Research Engineer, Staff Growth Engineer, and Senior Backend Engineer. [jobs.ashbyhq.com](https://jobs.ashbyhq.com/hedra)
- **Rapid Growth**: Yearly headcount growth of +108.7% and strong funding signal a high-growth trajectory with ample opportunity for career advancement. [linkedin.com](https://www.linkedin.com/company/hedra-labs)

## Sources
1. [hedra.com](https://www.hedra.com/)
2. [hedra.com/company](https://www.hedra.com/company)
3. [hedra.com/careers](https://www.hedra.com/careers)
4. [linkedin.com/company/hedra-labs](https://www.linkedin.com/company/hedra-labs)
5. [cbinsights.com/company/hedra](https://www.cbinsights.com/company/hedra)
6. [jobs.ashbyhq.com/hedra](https://jobs.ashbyhq.com/hedra)

## Other roles at Hedra

- [Product Marketing Lead](https://feeny.ai/job/product-marketing-lead-hedra-san-francisco-e3e47nfe303t) — San Francisco, CA
- [Senior Video Producer](https://feeny.ai/job/senior-video-producer-hedra-san-francisco-s53ek8b939wt) — San Francisco, CA
- [Head of Marketing](https://feeny.ai/job/head-of-marketing-hedra-san-francisco-8ayrt2dd5k6h) — San Francisco, CA
- [Account Executive](https://feeny.ai/job/account-executive-hedra-san-francisco-07yj5t908tqg) — San Francisco, CA
- [Customer Success Engineer](https://feeny.ai/job/customer-success-engineer-hedra-san-francisco-gkvaxfrqa35z) — San Francisco, CA
- [Senior/Staff Software Engineer, Distributed Systems](https://feeny.ai/job/senior-staff-software-engineer-distributed-systems-hedra-san-francisco-2j8k3yzfqbfw) — San Francisco, CA
- [Research Scientist](https://feeny.ai/job/research-scientist-hedra-san-francisco-hngsa0qcezzv) — San Francisco, CA
- [Research Engineer](https://feeny.ai/job/research-engineer-hedra-san-francisco-60yph5qfns3p) — San Francisco, CA
- [Inference Optimization Engineer](https://feeny.ai/job/inference-optimization-engineer-modular-united-states-canada-h70h6szsvg8e) — United States / Canada