Software Engineer, RL Environments & Evaluation Pipelines

davidjoseph-co; San Francisco (CA); On-site; USD 180,000 - 220,000; Full time

Benefits offered by this job

Competitive equity

Job summary

AfterQuery in San Francisco, CA is seeking a Software Engineer for RL Environments to design data slices and evaluation rubrics powering frontier model training.

You will own end-to-end data pipelines, experiment with RLHF/RLVR signals, and collaborate with research teams to translate training objectives into concrete data and evaluation specs. 1–4 years of software engineering experience required; on-site work. Competitive compensation with equity and rapid impact in a small, early-stage team.

Qualifications

• 1–4 years of software engineering experience.
• Design targeted data slices to surface model failure modes across domains.
• Build and iterate evaluation rubrics powering RLHF/RLVR pipelines.
• Develop quantitative frameworks to measure dataset quality, diversity, and impact on model alignment.
• Own end-to-end real-world and synthetic data pipelines, from scoping to production-ready evaluation specs.
• Run annotator modeling experiments to improve model capabilities.

Responsibilities

• Design data slices and explore data shapes that expose meaningful model failure modes across domains.
• Build and refine evaluation rubrics and reward signals for RLHF and RLVR training pipelines.
• Model annotator behavior and run experiments to improve model capabilities.
• Develop quantitative frameworks to measure dataset quality, diversity, and downstream impact on model alignment and capability.
• Create and manage both real-world and synthetic data pipelines.
• Partner with lab research teams to translate training objectives into concrete data and evaluation specs.

Skills

Software engineering

Data pipelines

RLHF/RLVR

Experimentation

Model evaluation

Job description

AfterQuery in San Francisco, CA is seeking a Software Engineer for RL Environments to design data slices and evaluation rubrics powering frontier model training.

You will own end-to-end data pipelines, experiment with RLHF/RLVR signals, and collaborate with research teams to translate training objectives into concrete data and evaluation specs. 1–4 years of software engineering experience required; on-site work. Competitive compensation with equity and rapid impact in a small, early-stage team.