Applied LLM Engineer: Fine-Tune, Align & Deploy AI Agents

Corepass; Menlo Park (CA); On-site; USD 150,000 - 190,000; Full time

Job summary

Corepass is building production-ready AI agents by training and aligning large language models for real business environments. The team focuses on model training, post-training, and deployment, creating end-to-end pipelines that translate research into revenue-driving applications.

We seek a skilled LLM Algorithm Engineer to own fine-tuning, domain-specific model development, evaluation, and integration into agent systems.

Qualifications

• Master’s degree or higher in CS/AI field.
• Strong DL and RL foundation.
• Transformer and large-scale training knowledge.
• Experience with LLM fine-tuning (SFT/DPO/RLHF) preferred.
• Proficient in PyTorch; Linux/GPU dev env familiarity.
• Strong ownership and continuous improvement mindset.

Responsibilities

• Own fine-tuning, post-training, and performance optimization for large language models.
• Build domain-specific LLMs, including data design, training, and evaluation.
• Lead model alignment efforts, including SFT, DPO, RLHF, and data strategy optimization.
• Explore RL applications in LLMs, including PPO and actor-critic methods.
• Build end-to-end model iteration loop: data, training, evaluation, improvement.
• Contribute to model inference optimization: distillation, quantization, acceleration, deployment.
• Support deployment of models in agent-based systems.

Skills

Deep learning

Reinforcement learning

Transformer architectures

Model fine-tuning

Hardware acceleration

PyTorch

Linux

Education

Master's degree

Tools

PyTorch

Linux

Job description

Corepass is building production-ready AI agents by training and aligning large language models for real business environments. The team focuses on model training, post-training, and deployment, creating end-to-end pipelines that translate research into revenue-driving applications.

We seek a skilled LLM Algorithm Engineer to own fine-tuning, domain-specific model development, evaluation, and integration into agent systems.