Staff Research Engineer, RL Systems & Pipelines (Remote)

SaidGig; New York (NY); Remote; USD 180,000 - 240,000; Full time

Benefits offered by this job

Up to 100% health-insurance premium Re

Paid time off

401(k) with company match

Remote-first workforce benefits

Job summary

SaidGig is seeking a research-focused reinforcement learning engineer to turn ambitious ideas into scalable training, evaluation, and data-generation capabilities for modern AI models. You will design RL environments, build training pipelines, and collaborate with a fast-moving research team to advance real-world applications.

This role offers equity and a remote-friendly setup, with compensation ranges reflecting seniority in a cutting-edge field.

Qualifications

• Deep reinforcement learning experience with environment design and training dynamics.
• Track record building and scaling RL systems, workflows, or experimentation frameworks.
• Experience with ML-oriented data design, synthetic-data pipelines, and RL workflows.
• Knowledge of automated evaluation, model validation, and QA processes.
• Experience fine-tuning and evaluating open-source ML models.
• Clear technical communication and writing skills.
• Ability to thrive in a fast-paced, research-driven, collaborative setting.

Responsibilities

• Design self-contained RL environments with reward functions and evaluation logic.
• Develop scalable episode pipelines and multi-component training processes.
• Create automated synthetic-data generation systems to speed training.
• Build AI-driven evaluation and QA systems for grading, feedback, and model assessment.
• Fine-tune and optimize open-source RL models using internal data and strategies.
• Establish benchmarking frameworks to assess model capability, robustness, and data quality.
• Contribute to releasing evaluations on internal and external benchmarks.

Skills

Deep RL

RL environ design

Experimentation frameworks

ML data design

Synthetic-data pipelines

Automated evaluation

Model fine-tuning

Technical communication

Fast-paced collaboration

Tools

Open-source ML models

RL infra tooling

Job description

SaidGig is seeking a research-focused reinforcement learning engineer to turn ambitious ideas into scalable training, evaluation, and data-generation capabilities for modern AI models. You will design RL environments, build training pipelines, and collaborate with a fast-moving research team to advance real-world applications.

This role offers equity and a remote-friendly setup, with compensation ranges reflecting seniority in a cutting-edge field.