Lead Post-Training AI Engineer (RL & Enterprise)

reflectionai; New York, California (NY, MO); On-site; USD 180,000 - 280,000; Full time

Benefits offered by this job

Top-tier compensation

Stock options

Health & wellness

Meals provided in office

Life & family benefits

Job summary

Reflection is a research lab focused on open, accessible AI, building models that customers can customize and deploy across enterprise environments.

As Forward Deployed Engineer Lead, Post-Training, you will own end-to-end strategy for model customization, from synthetic data to production deployment, working with customers and research teams.

Join us to scale post-training capabilities, shape best practices, and mentor engineers while delivering measurable outcomes for enterprise clients.

Qualifications

• Hands-on post-training experience with large language models at scale.
• Experience building synthetic data generation pipelines, reward models, and verifiers for reinforcement learning workflows.
• Deep understanding of evaluation methodology and how to interpret training dynamics.

Responsibilities

• Lead post-training engagements with enterprise customers: assess data, define training strategies, design reward signals and verifiers, prepare datasets, run training loops, and evaluate results.
• Design and build RL training environments, including synthetic data generation pipelines and preference data collection workflows.
• Design and build evaluation infrastructure: define metrics, build eval harnesses, curate test sets, and establish baselines.
• Own the data pipeline from raw customer data through training-ready datasets, including synthetic data generation and data quality checks.
• Deploy post-trained models across hybrid environments (cloud, VPC, on-prem) with cost and performance considerations.
• Shape the practice by defining playbooks, best practices, and mentoring engineers.

Skills

Post-training RL

Synthetic data generation

Reward modeling

Evaluation design

Distributed training

Leadership

Customer-facing

Automation & tooling

Tools

RL training frameworks

GPU clusters

Data pipelines

Job description

Reflection is a research lab focused on open, accessible AI, building models that customers can customize and deploy across enterprise environments.

As Forward Deployed Engineer Lead, Post-Training, you will own end-to-end strategy for model customization, from synthetic data to production deployment, working with customers and research teams.

Join us to scale post-training capabilities, shape best practices, and mentor engineers while delivering measurable outcomes for enterprise clients.