Lead ML Engineer – LLM Inference & NLP

About the role

Social Discovery Group is seeking a Lead ML Engineer to drive LLM inference and NLP initiatives across its remote, globally distributed team. You will lead technical efforts to scale large language models in production and guide both NLP and computer‑vision teams.

Key responsibilities

• Accelerate and scale LLM inference in production using techniques such as SGLang, KV and prefix caching, batching, quantization, and speculative decoding.
• Run distributed inference for models up to 1 trillion+ parameters across multi‑GPU and multi‑node environments.
• Benchmark new GPU hardware, integrate it into production, and adapt serving code.
• Provide technical leadership for NLP and CV teams: review experiments, set direction, and intervene early when needed.
• Train and fine‑tune language models, improve agent harnesses and chat algorithms.
• Track cutting‑edge research and open‑source work in inference and post‑training, translating findings into the ML roadmap.
• Collaborate with validation, content, and dataset teams to design experiments and measure model quality.

Required profile

• Deep hands‑on experience optimizing LLM inference in production (SGLang, vLLM, TensorRT‑LLM).
• Experience with distributed inference or training of large models (MoE, tensor/expert/pipeline parallelism, multi‑node GPU clusters).
• Strong understanding of inference performance factors (KV cache, attention kernels, batching, quantization, GPU profiling).
• Proven technical leadership, mentoring engineers while actively coding.
• Advanced English or Russian.

Required skills

• Python
• PyTorch and transformers libraries
• GPU profiling and optimization tools
• Backend development (Python, Go, C#) – a plus
• CUDA or Triton kernel development – nice to have
• Computer vision background – optional

What we offer

• Full‑time remote position.
• 28 vacation days plus 7 wellness days per year.
• Bonuses for successful referrals and professional training support.
• Health benefits reimbursement up to $1,000 per year.
• Equipment allowance for home or co‑working spaces.
• Internal gamified gratitude system with merchandise and activity rewards.