Researcher, Alignment Training (AI)

TL;DR

Researcher, Alignment Training (AI): Studying how frontier models acquire durable behavioral tendencies across the training stack with an accent on synthetic data, training objectives, and evaluation. Focus on designing training interventions and evaluation loops to ensure models are honest, reliable, and aligned with human intent.

Location: San Francisco, USA

Salary: $250k – $445k + Equity

Company

hirify.global is an AI research and deployment company dedicated to ensuring that general-purpose artificial intelligence benefits all of humanity.

What you will do

• Develop synthetic data methods to teach models higher-level behavioral tendencies, such as reasoning, honesty, and goal consistency.
• Study the impact of pre-training, mid-training, and post-training stages on downstream model behavior.
• Build evaluation loops that connect model behavior back to training data and objectives for faster iteration.
• Design reusable data generation and filtering pipelines to improve training data quality and robustness.
• Create experiments to distinguish durable learned behavior from benchmark gains or evaluation artifacts.
• Collaborate across alignment and product teams to translate research insights into improved model behavior.

Requirements

• Strong record of technically excellent work in large-scale ML, specifically in pre-training, post-training, synthetic data, or evaluation.
• Experience designing experiments where signals are subtle, noisy, or indirect.
• Ability to move seamlessly between research hypothesis formulation and engineering execution.
• Exceptional judgment regarding research priorities and the reliability of signals.
• Clear communication skills across research, engineering, and product contexts.
• Must be based in San Francisco

Culture & Benefits

• Opportunity to work on the core model training loop of frontier AI systems.
• Equity offers provided as part of the compensation package.
• Environment focused on the safe deployment of AGI to benefit humanity.
• Commitment to diversity and equal opportunity employment.