Software Engineer, RL Environments

David Joseph & Company; San Francisco (CA); On-site; USD 120,000 - 170,000; Full time

Job summary

David Joseph & Company in San Francisco is seeking a Software Engineer (Environments) to design datasets and evaluation rubrics that influence how frontier models learn. You will build data pipelines and run experiments to improve model capabilities.

The ideal candidate has 1–4 years of software engineering experience with a focus on data slices and evaluation rubrics, plus a background in AI safety or benchmarking work. This role offers hands-on impact at the cutting edge of AI research.

Qualifications

• 1–4 years of software engineering experience with a focus on designing data slices and evaluation rubrics.
• Background in AI safety or benchmarking organizations preferred.
• Experience with data pipelines and model evaluation.

Responsibilities

• Design datasets and evaluation rubrics that influence how frontier models learn.
• Build data pipelines and conduct experiments to improve model capabilities.

Skills

Software Engineering

Data Analysis

Model Evaluation

Data Pipelines

Quantitative Frameworks

Experiment Design

AI Safety

Benchmarking

Data Quality

Machine Learning

Reinforcement Learning

Data Structures

Model Training

Synthetic Data

Research Collaboration

Evaluation Rubrics

Job description

As a Software Engineer (Environments), you will design datasets and evaluation rubrics that influence how frontier models learn. You will work on building data pipelines and conducting experiments to improve model capabilities.

Requirements:

Candidates should have 1-4 years of software engineering experience with a focus on designing data slices and evaluation rubrics. A background in AI safety or benchmarking organizations is preferred, along with the ability to work on data pipelines and model evaluation.

Key Skills:

Software Engineering, Data Analysis, Model Evaluation, Data Pipelines, Quantitative Frameworks, Experiment Design, AI Safety, Benchmarking, Data Quality, Machine Learning, Reinforcement Learning, Data Structures, Model Training, Synthetic Data, Research Collaboration, Evaluation Rubrics