Optimize large-model inference at scale: improve throughput, reduce latency and cost per token, build benchmarking harnesses, tune parallelism and quantization strategies, implement load-balancing in routing, and evaluate custom kernels and emerging inference hardware.
Dragonfly is a crypto-native Venture Capital and research firm with $3.6B+ in assets under management and 160+ portfolio companies. Our Talent team connects people with roles across our portfolio, opening the door to opportunities through our Talent Network.
This is an application to join our talent network. This is not a listing for an internal role at Dragonfly.
We're actively sourcing for a Senior Inference Optimization Engineer for one of our portfolio companies building privacy-first consumer AI infrastructure. You'll be on the bleeding edge of LLM inference performance, pushing throughput, driving down latency, and optimizing cost per token at significant scale.
Location: Remote, USA (open to excellent candidates outside the USA)
What We’re Looking For:
- 5+ years in performance optimization or HPC with deep GPU architecture and parallel programming knowledge
- Hands-on experience with at least one production LLM inference engine (vLLM, SGLang) running at high volume
- Demonstrated experience with LLM inference optimization: continuous batching, PagedAttention, KV cache management, speculative decoding, quantization, CUDA graphs, torch.compile
- Experience with distributed inference strategies: tensor parallelism, pipeline parallelism, MoE parallelism in multi-GPU and multi-node environments
- GPU profiling fluency: Nsight Systems, Nsight Compute, PyTorch Profiler
- Proficiency in Python, Rust, or Go. C++/CUDA a strong plus
- Bonus: custom Triton kernels, diffusion/image model inference optimization, open-source inference framework contributions
About the role:
- Stand up and optimize GPU infrastructure including B300 nodes in owned data centers
- Drive down TTFT and TPOT, push throughput, and improve cost per token for LLM inference workloads
- Build reproducible benchmarking harnesses across inference engines to identify optimal engine, quantization scheme, and parallelism strategy per workload and GPU SKU
- Optimize multivariate inference load-balancing algorithms within the inference routing system
- Evaluate emerging inference optimization techniques including custom CUDA/Triton kernels, novel attention variants, new quantization schemes, and compilation stack improvements
- Evaluate emerging inference hardware (FPGAs, ASICs, custom silicon) for viability in the stack
Even if you don't match every point above but are an engineer passionate about AI and/or crypto, we encourage you to apply. There may be other opportunities that fit your skill set.
Process:
- We'll review your application and assess fit for this role.
- If there's a match, we'll facilitate a warm introduction to the team.
- If the timing isn't right, we'll keep you in mind for future opportunities across the portfolio.
Compensation
- Early Career: $110,000–$150,000
- Mid: $150,000–$200,000
- Senior: $180,000–$250,000
- Staff/Leadership: $230,000–$330,000
The compensation range reflects variation by seniority, location, and hiring company. Final compensation is confirmed with the specific hiring company.
Submit your information below, and we’ll reach out if there’s a potential fit.
Similar Jobs
Artificial Intelligence • Productivity • Software • Automation
Create motion design across product explainers, websites, paid social, events, campaigns, and product launches. Develop Zapier’s motion language, branded animation systems, motion guidelines, component libraries, and reusable templates. Collaborate with brand, product, marketing, web, social, agencies, and external partners. Produce storyboards, UI-based animations, scalable video formats, and experiment with AI and motion tools to help teams create on-brand assets independently.
Top Skills:
Ai Video ToolsFigmaFigma MotionJitter
Cloud • Healthtech • Social Impact • Software • Biotech
Drive new business and revenue growth across the Nordic territory by generating pipeline, managing complex SaaS sales cycles, forecasting accurately, presenting solutions, negotiating with technical and executive stakeholders, and closing strategic accounts. The role also involves account relationship management, collaboration with marketing, product, customer success, and channel teams, Salesforce data integrity, and use of structured sales methodologies such as MEDDICC.
Top Skills:
Artificial IntelligenceMeddiccSaaSSalesforce
Artificial Intelligence • Healthtech • Machine Learning • Natural Language Processing • Biotech • Pharmaceutical
Leads product strategy, roadmap, lifecycle ownership, adoption, and measurable outcomes for a greenfield enterprise AI platform. Defines platform boundaries, governance controls, evaluation, registration, and cost-tracking capabilities while translating evolving risk, privacy, security, and GxP requirements into usable product features. Partners with engineering, design, legal, compliance, risk, security, and global agent-building teams to prioritize investments, guide delivery, communicate direction, and drive platform adoption.
Top Skills:
AgileAIAi AgentsAi GovernanceGxpLeanModel Evaluation
What you need to know about the Melbourne Tech Scene
Home to 650 biotech companies, 10 major research institutes and nine universities, Melbourne is among one of the top cities for biotech. In fact, some of the greatest medical advancements were conceptualized and developed here, including Symex Lab's "lab-on-a-chip" solution that monitors hormones to predict ovulation for conception, and Denteric's vaccine for periodontal gum disease. Yet, the thousands of people working in the city's healthtech sector are just getting started, to say nothing of the tech advancements across all other sectors.
