Member of Technical Staff - ML Infrastructure & Performance

Embedding Vc

San Mateo, California, United States permanent

Posted: December 12, 2025

Interested in this position?

Create a free account to apply with AI-powered matching

Quick Summary

Improve Throughput, Latency, & Cost - deploying our models 2–10× faster & cheaper without quality regressions.

Required Skills

GPU Performance Serving Stack Parallelism Quantization/PEFT Systems Observability Autoscaling A/B Testing CUDA TensorRT

Job Description

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

Why Apply Through MisuJob?

AI-Powered Job Matching: MisuJob uses advanced artificial intelligence to analyze your skills, experience, and career goals. Our matching algorithm compares your profile against thousands of job requirements to find positions where you have the highest chance of success. This saves you hours of manual job searching and ensures you only see relevant opportunities.

One-Click Applications: Once you create your profile, applying to jobs is effortless. Your resume and cover letter are automatically tailored to highlight the most relevant experience for each position. You can apply to multiple jobs in minutes, not hours.

Career Intelligence: Beyond job matching, MisuJob provides valuable career insights. See how your skills compare to market demands, identify skill gaps to address, and understand salary benchmarks for your experience level. Make data-driven decisions about your career path.

Frequently Asked Questions

How do I apply for this position?

Click the "Register to Apply" button above to create a free MisuJob account. Once registered, you can apply with one click and track your application status in your dashboard.

Is MisuJob free for job seekers?

Yes, MisuJob is completely free for job seekers. Create your profile, get matched with jobs, and apply without any cost. We help you find your dream job without any hidden fees.

How does AI matching work?

Our AI analyzes your resume, skills, and experience to understand your professional profile. It then compares this against job requirements using natural language processing to calculate a match percentage. Higher matches mean better fit for the role.

Can I apply to jobs in other countries?

Absolutely. MisuJob features jobs from companies worldwide, including remote positions. Filter by location or look for remote opportunities to find jobs that match your preferences.

Ready to Apply?

Join thousands of job seekers using MisuJob's AI to find and apply to their dream jobs automatically.

Create Free Account Sign In

← Browse all jobs