Описание

Компания развивает платформу для персонализированного общения с AI-персонажами, дообучает open-source модели и работает с LLM до 1T параметров. Около 70% времени будет уделено hands-on engineering, без Project/People Management.

Обязанности

Оптимизация скорости, стоимости и стабильности inference больших LLM
Run distributed inference for very large models (up to 1T+ parameters) across multi-GPU and multi-node setups
Benchmark new GPU servers and hardware, bring them into production and adapt our serving code to them
Lead the NLP and CV teams technically: review experiments, set direction, and step in early when something is heading the wrong way
Train and fine-tune the language models behind our AI companions, and improve the agent harnesses and chat algorithm that run on them
Track cutting-edge research and open-source work in inference and post-training, and turn it into the ML roadmap
Collaborate closely with the validation, content, and dataset preparation teams to design experiments and measure model quality

Требования

Есть production-опыт оптимизации LLM inference: SGLang / vLLM / TensorRT-LLM
Работали с distributed inference/training больших моделей: MoE, tensor/expert/pipeline parallelism, multi-node GPU
Сильны в KV cache, attention kernels, batching, quantization, GPU profiling
Есть опыт training/fine-tuning и post-training: RLHF, DPO или аналоги
Уверенно работаете с PyTorch / Transformers
Proven technical leadership: you've guided engineers through reviews, mentoring and technical decisions while still writing code yourself
English B2+
Experience at AI-focused startups or companies is a strong plus
Backend engineering experience (Python, Go, C#) and knowledge of scalable deployment systems is a significant advantage

Будет плюсом

CUDA or Triton kernel development
A computer vision background. We also welcome strong CV leads who have accelerated large generative image or video models
Experience with multimodal LLMs
First-author papers or notable open-source work, e.g. contributions to SGLang, vLLM, or post-training libraries
A degree in CS, math, or physics from a strong program (MSc or PhD)

Условия

Distributed inference на multi-GPU / multi-node инфраструктуре: 32×H200 + AWS
Training и post-training LLM, развитие agent architectures
Техническое лидерство NLP/CV-команды и перспектива роста до Head of ML
Сильная команда, высокое вознаграждение, удаленно
Work from anywhere with our fully remote, full-time setup
Standard 28-day annual leave policy
7 yearly wellness days for life admin or recovery—no sick notes needed
Referral rewards up to $5000 for helping us hire top talent
We cover 50% of costs for training, conferences, and global meetups
Subsidized English classes through our corporate discount
Health support: receive up to $1,000 annually for medical fees or private insurance if you aren't on the group plan
Optimized workspace: we equip you in-office or provide $1000 every three years to perfect your home office or co-working setup
Peer-to-peer recognition: earn gratitude bonuses and swap them for swag, massage vouchers, or team adventures

Процесс отбора

Intro call — conversation with the hiring manager, includes a short live technical quiz (5 questions, camera on — no AI tools)
Technical interview — live coding session with AI tools allowed, plus ML and ML system design questions (90 min)
Final interview — culture fit and team alignment