Member of Technical Staff - ML Infrastructure & Performance
Quick Summary
Introducing Moonlake, AI for creating real-time interactive content Mission: Improve Throughput, Latency, & Cost - deploying our models 2–10× faster & cheaper without quality regressions. Scope of Work: - GPU performance: CUDA/Triton kernels, FlashAttention family, paged attention, CUDA Graphs.
Introducing Moonlake, AI for creating real-time interactive content
- GPU performance: CUDA/Triton kernels, FlashAttention family, paged attention, CUDA Graphs.
- Serving stack: TensorRT-LLM/Triton Inference Server, vLLM/TGI; continuous batching; on-GPU KV reuse; speculative decoding/medusa; mixture-of-agents routing.
- Parallelism: FSDP/ZeRO, TP/PP/expert parallel; NCCL tuning.
- Quantization/PEFT: AWQ/GPTQ/FP8; LoRA/DoRA serving.
- Systems: Ray/k8s/Argo, observability (Prom/Grafana/OpenTelemetry), autoscaling, A/B infra, canary + rollback.
Previous experience at Infra-heavy startups such as Databricks, Roblox
We are committed to being an on-site, in-person team currently based in San Mateo
Location & Eligibility
Listing Details
- Posted
- December 12, 2025
- First seen
- May 6, 2026
- Last seen
- May 8, 2026
Posting Health
- Days active
- 0
- Repost count
- 0
- Trust Level
- 12%
- Scored at
- May 6, 2026
Signal breakdown
Please let embedding-vc know you found this job on Jobera.
4 other jobs at embedding-vc
View all →Explore open roles at embedding-vc.
Similar Member Of Technical Staff jobs
View all →
Xai
AxonAxonAxonBrowse Similar Jobs
Stay ahead of the market
Get the latest job openings, salary trends, and hiring insights delivered to your inbox every week.
No spam. Unsubscribe at any time.