◆ AfterJournal
AI apps, startups and the people building them
Author guidelines
·
Write for us
·
Contact
Jobs
/ MLOps / Software Engineer, Training/Inference (C++)
Software Engineer, Training/Inference (C++)
xAI · Palo Alto, CA; Seattle, WA
◉ On-site
◆ MLOps ▣ Full-time ⏫ Mid-level $ USD 160k-250k/year
Apply now →
0 applied · 0 views
xAI is hiring a software engineer for training and inference in C++. The role covers serving large models for Grok at scale.
- Design and tune large scale model serving systems
- Build global caching, batching, load balancing and auto-scaling
- Optimize GPU kernels, quantization and speculative decoding
- Reduce tail latency
Requirements
- Strong C++ skills
- Experience with distributed systems or GPU programming
- Knowledge of model inference
This is a on-site full time position at mid level level, based in Palo Alto, CA; Seattle, WA.
Day to day work includes building platforms, tuning performance and keeping services reliable.
Candidates should check the full posting for exact qualifications, pay and benefits.
Application steps, interview stages and start dates are listed on the original posting.
Apply on the company's careers page.
Similar jobs
◆ Newsletter
Ideas worth your inbox.
The best new stories, startups and AI tools every week. No noise, unsubscribe anytime.