LLM Modeling & Post-Training Engineer

Sourced from lawrenceharvey.com

• Design, train, evaluate, and optimize large language models for enterprise use cases involving complex reasoning, domain specialization, structured outputs, and workflow execution.
• Work across the full post-training lifecycle: supervised fine-tuning (SFT), reinforcement learning and alignment, preference optimization, reward modeling, synthetic data generation, evaluation, model safety, and distributed training.
• Collaborate with platform engineers, domain experts, AI architects, and product leaders to translate business requirements into reliable AI systems.

• Hands-on experience with fine-tuning and aligning open-weight or proprietary foundation models using techniques such as SFT, RLHF, PPO, DPO, GRPO, RLAIF, LoRA, and QLoRA.
• Understanding how post-training methods impact reasoning quality, safety, latency, cost, and production reliability.
• Ability to bridge frontier AI research with practical enterprise deployment.