Applications are closed for this role. It was originally posted 2025-12-12. It’s no longer accepting applicants — see roles Embedding VC is still hiring for →, or browse the live openings below.
About this role
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.
- 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.
Tech signals:
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
Tech stack
LLMDatabricks
Still hiring at Embedding VC
Growth Engineer - Globalization
Engineering
$300K–$400K
Senior/Staff Frontend Engineer
Engineering
$100K–$200K
Senior/Staff Product Engineer
Engineering
$100K–$200K
See all live roles at Embedding VC →Similar roles at other companies
N
Senior Member Technical Staff (MTS 3) - Machine learning
Operations
P
Member of Technical Staff
Operations
X
Member of Technical Staff - RL Inference
Operations
$180K–$440K
L
Member of Technical Staff - Applied ML, Japanese Multimodal
Operations
See all Operations roles →