🚀 Hiring: Lead ML Engineer (Remote, Full-time)

We're building a platform for AI-lationships — emotionally intelligent connections between people and AI characters. Open-source models, real AI agency, no ChatGPT wrappers.

The role: Own the performance and technical direction of our LLMs. ~2/3 hands-on: making 1T+ parameter models run faster and cheaper on distributed GPUs. The rest: technical leadership of NLP/CV engineers. You lead through expertise, not project management.

Must-have:

• Deep hands-on LLM inference optimization (SGLang, vLLM, TensorRT-LLM)
• Distributed inference/training: MoE, tensor/expert/pipeline parallelism, multi-node clusters
• KV cache, attention kernels, batching, quantization, GPU profiling
• Training/fine-tuning LLMs incl. post-training (RLHF, DPO)
• Proven technical leadership + still writing code
• PyTorch, transformers
• Advanced English or Russian

Nice to have: CUDA/Triton, CV background, multimodal LLMs, open-source contributions, MSc/PhD.

Why join: Fully remote

• 28-day leave + 7 wellness days
• 50% training coverage
• health support up to $1000/yr
• $1000 every 3 years for workspace
• clear path to Head of ML

Process: Intro call → Tech interview (90 min) → Final.