Lead ML Engineer
Core
Lead technical optimization of LLM inference and NLP/CV teams for global social discovery platforms.
Role type
Senior IC Lead ML Engineer (LLM Inference & NLP)
Builds
Distributed inference systems for large models (1T+ parameters), agent harnesses, and chat algorithms.
Domain
AI/ML, Large Language Models, Social Discovery
Deliverable
production ML models
Required skills
LLM inference optimization (SGLang, vLLM, TensorRT-LLM), distributed inference/training (MoE, parallelism), KV cache management, LLM fine-tuning (RLHF, DPO), PyTorch, technical leadership, GPU profiling
Preferred skills
CUDA/Triton kernel development, Computer Vision, Multimodal LLMs, Open-source contributions
Technologies
SGLang, vLLM, TensorRT-LLM, PyTorch, transformers, CUDA, Triton
Responsibilities
Scale LLM inference across multi-GPU/multi-node setups, benchmark and integrate new GPU hardware, lead NLP and CV teams technically, train and fine-tune language models, track cutting-edge research for the ML roadmap, collaborate with validation and dataset teams on model quality.
Seniority
Senior, hands-on IC with leadership responsibilities