Principal Engineer Model Performance
Runware
Runware is the AI inference platform that builds and runs its own infrastructure, end to end. Our has served more than 20 billion requests for over 1 million developers and 500 million end users, with 400,000+ models behind a single integration, at up to 10x lower cost per token than traditional providers.
We are now building the AI Factory that runs it. The packs 1 MW of custom-designed compute into a 20-foot container with closed-loop, water-free cooling, sited wherever power exists. Pods are live in the US and Europe, and we are scaling to dozens of pods and tens of thousands of GPUs, all operated as one distributed fabric that reroutes traffic the moment a pod goes offline ().
Every request that hits that fleet, whether it is an image, a video, a voice or a token stream, has to come back faster and cheaper than anyone else can serve it. Model performance is what makes that true. That is the job.
The role
As Principal Engineer, Model Performance, you will own how fast and how cheaply every model on Runware runs: diffusion and video generation, speech, 3D and LLMs, across 400,000+ models and tens of thousands of GPUs. You will set the performance roadmap, build the hardest pieces with your own hands, and build and lead the Model Performance team as it grows around you.
This is a principal-level role for someone who has led inference performance work at the frontier and still writes the kernel. You will decide where the next 2x comes from on a given model and hardware generation, whether that is a fused attention kernel, a better quantization recipe, speculative decoding, a smarter batching policy or a different parallelism layout, and then make it land in production on real traffic. You will work directly with the Sonic Inference Engine team, the infrastructure and hardware teams, and with NVIDIA and the open-source engine communities, and you will hire, mentor and lead the engineers who do this work alongside you.
Success means Runware serves a new open model at the Pareto frontier of latency and cost within days of its weights being released, our cost per request keeps falling with every hardware generation, and the team you have built can do this without you in the loop.
What you'll do
- Own inference performance end to end for the fleet: the kernels, the serving engines, the model-level optimizations and the benchmarks that prove them, across image, video, audio, 3D and LLM workloads on every GPU generation we run.
- Set the model performance roadmap. Decide which models, hardware and techniques get the team's attention and in what order, based on real traffic, real cost and what the next generation of pods will run.
- Do the hardest work yourself: write and tune CUDA kernels, fuse attention and MLP paths, bring up new quantization formats (FP8, FP4, INT4) with quality held, and get new parallelism and batching strategies working on multi-GPU nodes.
- Make new models fast on day one. Build the pipeline that takes a newly released open model from weights to a production-grade, optimized deployment in days, and keep closing that gap.
- Choose and shape the serving stack: TensorRT-LLM, vLLM, SGLang, custom diffusion and video pipelines, and the Sonic Inference Engine's own runtime. Decide what we adopt, what we fork and what we write ourselves, and contribute upstream where it pays.
- Own the benchmarking and performance regression system: reproducible, hardware-aware measurement of throughput, latency, cost and quality for every model we serve, wired into CI so that a regression never reaches a pod.
- Partner with infrastructure and hardware engineering on GPU memory, storage and network bottlenecks that show up as inference latency, and feed what you learn back into the next generation of servers and pods.
- Build and lead the team. Hire principal and senior engineers, set the bar for technical rigour, mentor the people on the team, and run it so that a very small group delivers performance across a very large model catalogue.
- Use AI to accelerate the work: automated kernel search and tuning, benchmark generation, profiling triage and documentation with LLM-based agents, so that the team's output grows faster than its headcount.
Requirements
What we're looking for
- 10+ years in GPU, HPC or deep learning systems engineering, with several of those optimizing inference performance for models in production at a company that runs them at scale.
- A track record of shipping performance, not just measuring it. You have taken a state-of-the-art model from a reference implementation to the Pareto frontier of latency and cost on real hardware, and you know what breaks between the two.
- Deep, current, hands-on CUDA and GPU architecture expertise: kernel design, memory hierarchy and occupancy, Tensor Cores, fused kernels, CUDA Graphs, NCCL, and the profilers (Nsight Systems and Compute) that show exactly where a microsecond goes.
- Real production experience with at least one major inference engine (TensorRT-LLM, vLLM, SGLang or similar) and with the techniques that define modern serving: continuous batching, paged KV cache, speculative decoding, prefill/decode disaggregation, quantization and tensor, pipeline and expert parallelism.
- Fluent in Python and C++, comfortable in PyTorch internals, torch.compile and Triton, and happy to write the benchmark, the kernel and the CI job yourself rather than waiting for someone else to.
- Experience leading engineers: you have built or run a performance team, hired for it, set its technical direction and stayed hands-on while doing so.
- You use AI to accelerate your own output every day, for kernel search, profiling analysis, benchmarking, documentation and code review, and you have a clear view of how a small team armed with these tools should operate differently.
- Comfortable owning outcomes in a fast-moving, ambiguous environment, making decisions with incomplete information and being accountable for latency, cost and quality across hundreds of thousands of models.
Nice to have
- Diffusion and video generation performance: DiT and UNet pipelines, attention at long sequence lengths, step distillation, caching across denoising steps, LoRA hot-swapping, and the loaders and samplers in ComfyUI, Diffusers or custom engines.
- Contributions to TensorRT-LLM, vLLM, SGLang, FlashAttention, CUTLASS, Triton, Dynamo or similar open-source inference projects, or an open-source project of your own that people run.
- Experience with Blackwell-generation hardware (B200, GB200/GB300 NVL72), NVLink and NVSwitch topologies, and multi-node inference over InfiniBand or RoCE.
- Mixture-of-experts serving: expert parallelism, expert placement and load balancing, and the memory and communication trade-offs that come with them.
- Accuracy evaluation for optimized models: the harnesses, datasets and statistical discipline to prove a quantized or distilled model is as good as the original.
- Experience with non-NVIDIA accelerators (AMD, TPU or custom silicon) and with porting an inference stack across them.
- Speech and audio model serving: streaming ASR and TTS with tight latency budgets.
- Published work, patents or talks on inference performance.
Benefits
What we offer
- A rare mandate: own inference performance for one of the largest model catalogues in the world, on hardware the company designs and operates itself, at a business whose margin is your work, with the GPU budget and backing to match.
- Meaningful stock options.
- We're a remote-first collective, meeting in person twice a year to plan, brainstorm and celebrate wins. We keep core hours for collaboration and calls; outside those, you set your own schedule.
- Our release cycles are fast and intense, and they're followed by real downtime. We expect you to take it.
- Generous paid time off, including vacation, sick days and public holidays.
- Paid maternity, paternity and caregiver leave.
- Twice-yearly company retreats in inspiring locations.
$208k - $312k
...a dataflow architecture rather than the traditional GPU model. Its decode performance is especially strong for agentic workloads like multi-turn... ...qualifications ~ B.S. in Computer Science, Electrical Engineering, or related field ~8+ years of industry experience in ML...PerformanceFull timeTemporary workLocal areaWorldwideFlexible hours$216.2k - $394k
...— you’ll add something!DescriptionAs a Senior Staff/Principal Engineer on the Foundation Model Compute Infrastructure team, you will architect, build... ...foundation model researchers and engineers to improve performance, reliability, scalability, and developer productivity...PerformanceRelocation$206.2k - $356.4k
...patterns through multimodal sensing and AI models. This team combines advanced machine... ...for a manager to lead a talented group of engineers who evaluate the algorithms and AI... ...monitoring that qualify features, measure performance and system memory usage, and track quality...PerformanceRelocationShift work$200k - $351k
...City: San Jose Summary Celestica Engineering is seeking a highly motivated and self-... ...Experienced working with component models (touchstone files) and cascading models... ...Significant experience with measuring signal performance in the lab: TDR measurements and VNA...PerformanceLocal areaFlexible hours$148k - $200k
...differentiate their products with higher performance, smaller size, lower power, and better... ...ll build and lead a team of validation engineers shaping the next generation of MEMS... .... Job Details Job Summary The Principal Product Validation Engineer will lead and...PerformanceLocal area$160k - $200k
...people for both external and internal opportunities. At Fujifilm, performance, development and accountability are the standards to which the... ...teams including R&D, sustaining and process development engineers and manufacturing operations. Propose, evaluate, and implement...PerformanceWork at officeFlexible hours- ...Principal EngineerAt F5, we strive to bring a better digital world to life. Our teams empower... ...thrive.About the RoleAs a Principal Engineer at F5, you will play a hands-on... ...resource definitions (CRDs), and high-performance proxy plugins that seamlessly bridge multi...PerformanceLocal area
$107.5k - $204.5k
...of experience and renowned engineering expertise to meet the needs... ...department is seeking to hire a Principal Engineer - One Shots. This... ...Present one shot device design models and supporting analyses/test... ...our actions, behaviors, and performance with a vision for a safer,...PerformanceContract workTemporary workFor contractorsWork experience placementFor subcontractorWork at officeRemote workRelocationFlexible hours$233.99k - $383.46k
...Description: The Role and Impact As a Principal Engineer, Software Application Architecture, you... ..., and protocols to ensure optimal performance. Business group Intel's Software group... ...Drive the crash analytics and reliability modeling stack that accelerates root cause...PerformanceFull timeLocal areaImmediate startShift work- ...com is building a 100× better job search engine — fast, comprehensive, honest, and... ...who can help us turn powerful AI and ML models into fast, reliable production systems.... ...someone who loves the details of model performance, GPU utilization, inference architecture...PerformanceFull timeRelocation package
$219k - $351k
...becoming a memory-bandwidth business. As models scale past what any single GPU can... ...afterthought.We are looking for a Hands-on Principal Engineer who combines deep, first-principles... ...not just their flags. Drive inference performance engineering: continuous batching,...PerformanceWork at officeRemote workFlexible hours- ...: Architect, Analyze and optimize high-performance SoCs for Cloud computing, and machine learning... ...performance architect on our design engineering team, you will propose and implement... ...exploration, performance modeling, and analysis for next-generation GPU and...PerformanceFull time
- ...interconnects to scalable photonic engines, Lumilens is unlocking a new... ...We are seeking a Principal Engineer, Silicon Photonics... ...optical interconnects, balancing performance, manufacturability, cost,... ...analysis, using simulation and modeling to assess impairments like...PerformanceFull timeContract workWork at office
$220k - $290k
...generation microLED technologies for high-performance computing and augmented reality (AR)... ...to help create the optical communication engines that will power the future of scalable AI... ...backplanes. Build Data-Driven Performance Modeling: Utilize carrier transport and optical...Performance$114.6k - $234.6k
...operational analysis while maintaining engineering, security, and quality standards. Write... ...-scale distributed systems, network modeling software, network measurement platforms... ...data structures, system reliability, and performance engineering. ~ Experience with one or...PerformanceTemporary workFlexible hours$219k - $273.7k
...We are seeking an experienced Materials and Processes (M&P) Engineer to serve as the Metallics Subject Matter Expert (SME) for the airframe... ...are slightly impatient flexible under changing priorities and perform under pressure. What youll do Technical authority: Serve...PerformanceFull timeLocal areaWorldwideVisa sponsorshipFlexible hours$133.5k - $272k
...including more than 30 of the Fortune 100, trust the Netskope One platform, its Zero Trust Engine, and the powerful NewEdge network to gain full visibility and control without performance trade-offs. At Netskope, our technology is driven by our greatest strength: our...Performance- ...a dataflow architecture rather than the traditional GPU model. Its decode performance is especially strong for agentic workloads like multi-turn... ...inference and HPC applications. We are searching for a software engineer who will work on all parts of the runtime stacks,...PerformanceFull timeTemporary workLocal areaWorldwideFlexible hours
$219k - $351k
...The role includes debugging emulation performance and area issues, as well as developing... ...Own and maintain chip level emulation models for validating different subsystems within... ...BS in Computer/Electrical/Electronic Engineering or Computer Science, and 20 years of relevant...PerformanceWork at officeFlexible hours$196.2k
...connects, powers up, or thinks? As a Principal Engineer Firmware in our Research & Development... ...issue reproduction Tune end-to-end performance with measurable goals —for example... ..., MBSE repositories, or architecture modeling tools (commercial or open) in hardware...PerformanceFull timeLocal areaRemote work$170k - $200k
...highly respected environmental engineering and civil infrastructure... ...About the Position The Principal – Water/Wastewater Engineer... ...technical resource for hydraulic modeling, condition and vulnerability... ...strategy, financial performance, staffing, and market expansion...PerformanceContract workRemote work$184k - $287.5k
...with AI, and the Relational Foundation Model team is helping lead that transformation... ...a new frontier for enterprise AI. As an engineer on this team, you will go beyond adapting... ...to post-training optimization and high-performance inference. This is an opportunity to turn...PerformanceFull time$97.68k - $173k
...Description U.S. Bank is seeking the position of Quantitative Model Analyst in Cupertino California. Essential... ...and services. The position evaluates model conceptual soundness performance implementation and ongoing monitoring to ensure alignment with...PerformanceFull timeTemporary workBank staffLocal areaWork from home$107.5k - $204.5k
...the strength of more than 100 years of experience and renowned engineering expertise to meet the needs of today’s mission and stay ahead... ...What We Offer Our values drive our actions, behaviors, and performance with a vision for a safer, more connected world. At RTX we value...PerformanceTemporary workApprenticeshipWork experience placementInterim roleWork at officeRemote workRelocationFlexible hours- ...State/Province: Texas City: Austin Summary The Principal Power Engineer develops new electrical systems/circuits for various applications... ...design and simulations. Detailed Description Performs tasks such as, but not limited to, the following: Work autonomously...PerformanceFor contractorsWork experience placementWork at officeLocal area
$135.2k - $306.4k
...contributing to Linux kernel and working on innovative projects across multiple kernel subsystems, including networking, storage, security, performance optimization, virtual memory management, architecture enablement, and live patching technologies. Responsibilities Design,...PerformanceTemporary workFlexible hours$163.2k - $264k
...flexibility when it's needed. This model supports real-time problem-... ...Job Summary The Team Engineering - Our engineering team is at... .... Job Summary As a Principal Software Engineer, you will... ...and pipelines to improve performance, ensure smooth production integration...PerformanceFull timeWork at office$114.6k - $234.6k
..., and packaging, ensuring reliability, performance, and manufacturability. Utilizes advanced... ...aided design (CAD) tools to develop 3D models and detailed designs in collaboration... .... Manages mechanical design aspects of engineering projects, ensuring alignment with project...PerformanceTemporary workFlexible hours$114.6k - $234.6k
...products, ensuring they meet functional, performance, power efficiency, security, and... ...problems. -Performs complex sustaining engineering activities such as resolving customer escalations... ...Cloud Systems & Appliances. As a Principal Board Engineer, you will be responsible...PerformanceTemporary workFlexible hours$107.5k - $204.5k
...the strength of more than 100 years of experience and renowned engineering expertise to meet the needs of today’s mission and stay ahead... ...and 1000V. What You Will Do Working with a team of engineers performing electrical tests and troubleshooting on subassemblies,...PerformanceTemporary workWork experience placementInterim roleRelocationFlexible hours
Do you want to receive more vacancies?
Subscribe and receive similar vacancies to Principal Engineer Model Performance. Be the first to apply!
- principal cloud engineer San Jose, CA
- senior civil engineer project manager San Jose, CA
- principal developer San Jose, CA
- principal data engineer San Jose, CA
- principal engineer San Jose, CA
- director systems engineering San Jose, CA
- principal application developer San Jose, CA
- director data engineering San Jose, CA
- hotel chief engineer San Jose, CA
- general engineer San Jose, CA



