Joi AI
Lead ML Engineer — LLM Inference & NLP
2 нед. назад
Страна неизвестнаLeadRemoteC1
pytorchdistributed inferencepythongoc#nlpinference optimization
Joi Lab is an open research arm building open-source generative models and training infrastructure focused on true AI agency. The role involves handling huge models, optimizing fast and cheap inference, and setting technical direction for NLP and CV engineers.
О компании
- Joi Lab (joilab.ai) is our open research arm — we build open-source generative models, agent architectures, and training infrastructure. All code, weights, and data are public.
- We're not chasing the next ChatGPT wrapper; we're working on true AI agency: persistent memory, self-modification, self-authored.
Обязанности
- You make huge models, up to 1T+ parameters, answer fast and cheap in production.
- SGLang, caching, distributed inference, post-training.
- You also set the technical direction for our NLP and CV engineers.
Требования
- 5+ years of experience in ML engineering
- Deep hands-on experience optimizing LLM inference
- Proficiency with PyTorch and related libraries
- Experience with distributed inference/training of large models
- Strong understanding of inference optimization techniques
- Proven technical leadership in guiding engineers
- Backend engineering experience (Python, Go, C#)
- Advanced English or Russian language skills