Principal Engineer, Model Optimizations

The posting, as DigitalOcean wrote it

Dive in and do the best work of your career at DigitalOcean. Journey alongside a strong community of top talent who are relentless in their drive to build the simplest scalable cloud. If you have a growth mindset, naturally like to think big and bold, and are energized by the fast-paced environment of a true industry disruptor, you’ll find your place here. We value winning together—while learning, having fun, and making a profound difference for the dreamers and builders in the world.

We are looking for a Principal Engineer to own how models are optimized for serving across our entire accelerator fleet—NVIDIA and AMD alike.

DigitalOcean is the Inference Cloud. The Inference Platform team runs frontier open models in production on a heterogeneous GPU fleet, and the gap between a model that merely runs and a model that runs well is measured in millions of dollars of GPU time and in whether a customer's SLO is met. Closing that gap is this role.

You will own the model optimization discipline end to end: quantization strategy and its accuracy budget, kernel selection and authoring, attention and MoE execution, speculative decoding, and the parallelism layout that ties them together. You'll do it across model architectures that change every few months and across two vendor stacks with genuinely different performance characteristics—CUDA/Hopper/Blackwell on one side, ROCm/MI300-class and beyond on the other. The hard part is not making one model fast on one GPU. It's building the methodology, tooling, and upstream relationships that make every model fast on every GPU we buy, and doing it fast enough to launch a new model the week it drops.

What You'll Be Doing

• Setting the technical strategy for model optimization across the fleet: which techniques we invest in, which we consume upstream, and how we decide
• Owning quantization end to end—FP8, FP4/MXFP4, INT8, weight-only schemes such as AWQ and GPTQ—including calibration methodology, the accuracy budget we're willing to spend, and the eval gates that enforce it
• Driving performance for modern architectures at the execution level: MoE routing and fused expert kernels, MLA and GQA attention variants, long-context and sliding-window attention, and the memory-movement patterns each implies
• Leading speculative decoding work (draft models, EAGLE/Medusa-class methods, n-gram and lookahead approaches) and the acceptance-rate tuning that determines whether it actually pays
• Writing and tuning kernels where upstream falls short—CUDA, Triton, CUTLASS, and their ROCm counterparts (HIP, Composable Kernel, hipBLASLt, AITER)—and knowing when not to
• Establishing how we choose parallelism layouts (TP, PP, EP, attention DP) per model, per GPU family, per traffic shape, and encoding that into something repeatable rather than tribal knowledge
• Building the benchmarking and regression infrastructure that makes optimization claims trustworthy: agent-shaped and long-context traffic distributions, TT

[…]
ofessional development and provides resources to support your growth. We provide employees with reimbursement for relevant conferences, training, and education, subject to company policy.

• We care about your well-being. We take a comprehensive approach to our total rewards packages because we know different things drive different people. Our benefits are designed to support you and may include flexible time off, local team meetups, and mental health and well being support. Our benefits philosophy is consistent globally, but specific benefits and eligibility vary by location to reflect local needs and regulations.
• We reward our employees. The salary range for this position is based on market data, relevant years of experience, and skills. Eligible employees may also receive equity compensation, which may include a new hire equity grant and, in participating countries, the opportunity to participate in our Employee Stock Purchase Program. Equity awards are subject to approval and the terms of the applicable plan.
• Non-sales roles : In addition to base salary, this role is eligible to participate in DigitalOcean’s annual bonus plan and may be eligible for a new hire equity grant, subject to plan terms and local eligibility. Bonus amounts depend on company and individual performance.
• Sales roles (sales compensation eligible) : In addition to base salary, this role may be eligible to earn incentive compensation under the applicable sales compensation plan and may be eligible for a new hire equity grant, subject to plan terms and local eligibility.
• DigitalOcean is an equal-opportunity employer. We do not discriminate on the basis of race, sex, disability, protected veteran status, or any other characteristic protected by applicable law.

Application Limit: You may apply to a maximum of 3 positions within any 180-day period. This policy promotes better role-candidate matching and encourages thoughtful applications where your qualifications align most strongly.