Post-Training AI Lead for Enterprise RL & Evaluation

Reflection AI; New York (NY); On-site; USD 180,000 - 240,000; Full time

Benefits offered by this job

Stock options

Health insurance

Meals provided

Parental leave

Unlimited PTO

Visa sponsorship

Team off-sites

Job summary

Reflection AI in New York seeks a Forward Deployed Engineer Lead, Post-Training to define and scale model customization workflows for enterprise customers. You will own data pipelines, synthetic data, reward modeling, and production deployment across cloud, VPC, and on-prem environments.

You will lead RL training environments, design evaluation strategies, mentor engineers, and collaborate with research and customer teams to deliver measurable outcomes and robust post-training capabilities at

Qualifications

• Experience leading post-training efforts for large language models at scale.
• Built RL training environments and synthetic data workflows.
• Designed evaluation strategies to measure real-world performance.

Responsibilities

• Lead post-training engagements with enterprise customers and define training strategies.
• Design and build RL training environments and synthetic data pipelines.
• Create evaluation infrastructure and baselines for customer use cases.
• Own data pipelines from raw data to training-ready datasets.
• Deploy post-trained models across cloud, VPC, and on-prem environments.
• Mentor engineers and establish best practices for applied AI work.

Skills

Post-training RL

LLM deployment

Reinforcement learning

Distributed training

Data pipelines

Production code

Customer-facing tech

Tools

Multi-node GPU clusters

RL training infra

Job description

Reflection AI in New York seeks a Forward Deployed Engineer Lead, Post-Training to define and scale model customization workflows for enterprise customers. You will own data pipelines, synthetic data, reward modeling, and production deployment across cloud, VPC, and on-prem environments.

You will lead RL training environments, design evaluation strategies, mentor engineers, and collaborate with research and customer teams to deliver measurable outcomes and robust post-training capabilities at