Member of Technical Staff, LLM Post-Training, Applied

What you'll do

• Lead instruction tuning, preference tuning, and model alignment; own customer projects from requirements and data generation through training, evaluation, and delivery.
• Customize open-source models and optimize inference for production efficiency, reliability, and robustness.
• Provide technical mentorship and develop reusable tooling and workflows.

What they ask for

• 5+ years building and deploying machine-learning-based services in production.
• Hands-on experience with data generation and evaluation for LLM post-training, and text-specific post-training workflows.
• Experience training or fine-tuning models using SFT, instruction tuning, RLHF, DPO, or similar preference alignment methods.
• Experience on Agentic AI; proficiency with the open-source ML ecosystem (Hugging Face, PyTorch) and modern model architectures.

Nice to have

• Experience optimizing inference, including on-premise deployments, or improving deployed-model performance and scalability.
• Experience with inference optimization frameworks (vLLM, SGLang, TensorRT), Kubernetes, or external-customer applied ML delivery.

Tools

Hugging Face, PyTorch, SFT, RLHF, DPO, vLLM, SGLang, TensorRT

AI focus

Applied LLM post-training, including data generation, instruction and preference tuning, alignment, evaluation, and inference optimization for production deployments.