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.
Submit your information below, and we’ll reach out if there’s a potential fit.
Similar Jobs
Artificial Intelligence • Legal Tech
Lead GC AI's EMEA expansion from zero-to-one: own regional revenue, close enterprise deals, hire and lead sales and cross-functional teams, drive localized marketing and demand generation, and implement scalable sales processes and KPIs to build a repeatable European business.
Top Skills:
Ai-Driven SoftwareLegal Text Processing
Artificial Intelligence • Machine Learning • Natural Language Processing • Software • Conversational AI
The Account Executive will build a sales pipeline in the German markets, work with cross-functional teams, and maintain stakeholder relationships to drive sales and manage accounts for Deepgram's voice AI platform.
Top Skills:
AISales TechnologySpeech-To-SpeechSpeech-To-TextText-To-SpeechVoice Ai
Artificial Intelligence • Machine Learning • Natural Language Processing • Software • Conversational AI
Sell Deepgram's voice AI platform across EMEA by prospecting new logos, building pipeline, closing full-cycle technical deals, collaborating with Sales Ops and Sales Engineers, managing stakeholder relationships, and driving upsell with CSMs. Target technical buyers and communicate product value to meet and exceed quotas.
Top Skills:
Ai/MlCloud ApisDeveloper ToolsSpeech-To-TextText-To-SpeechVoice Ai
What you need to know about the Toronto Tech Scene
Although home to some of the biggest names in tech, including Google, Microsoft and Amazon, Toronto has established itself as one of the largest startup ecosystems in the world. And with over 2,000 startups — more than 30 percent of the country's total startups — Toronto continues to attract new businesses. Be it helping entrepreneurs manage their finances, simplifying business operations by automating payroll or assisting pharmaceutical companies in launching new drugs, the city's tech scene is just getting started.
