Forward Deployed Engineer, Lead - LLM Post-training

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

Benefits offered by this job

Top-tier compensation

Stock options

Health & wellness

Meals provided

Parental leave

Job summary

Reflection is a research lab focused on making intelligence open and accessible, building open models you can customize and deploy. We seek a Forward Deployed Engineer Lead, Post-Training, to own the technical strategy for model customization from data generation to production deployment.

You will work with customers to understand their needs and collaborate with research teams to push what’s possible with our models, shaping the post-training and evaluation practice at scale.

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.
• Practical experience with training infrastructure at scale: multi-node GPU clusters, distributed training, and cost optimization.
• Strong software engineering fundamentals with production-quality code and reproducible workflows.

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 against customer-specific benchmarks.
• Design and build RL training environments, including synthetic data generation pipelines, reward model training, and preference data collection workflows.
• Design and build evaluation infrastructure: define what better means for each customer use case, 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, data quality inspection, cleaning, and format standardization.
• Deploy post-trained models across hybrid environments (public cloud, VPC, on-premises), ensuring inference performance and cost efficiency at scale.
• Shape and scale the post-training practice by defining playbooks, best practices, and technical standards; mentor engineers on the team.

Skills

LLM post-training

RL training

Data pipelines

Software engineering

Customer-facing

Ownership

Multi-node GPU

Tools

Python

PyTorch

Git

Job description

Our Mission

Reflection is a research lab making intelligence open and accessible for everyone to use, customize, and build on. We build open models that let anyone control their intelligence and help shape the future of AI. Our mission: make intelligence open and accessible to all.

Role Overview
We're seeking an exceptional technical leader to build and scale Reflection's post-training and evaluation capabilities within the Applied AI team. This team works at the intersection of model adaptation, sovereign deployment, and enterprise deployment: taking Reflection's open-weight models and making them work for specific customer domains, tasks, and constraints. As a Forward Deployed Engineer Lead, Post-Training, you will own the end-to-end technical strategy for model customization, from synthetic data generation and reward modeling through training and production deployment. You will work directly with customers to understand their needs and with research teams to push what's possible with our models.

What You'll Do

• Lead post-training engagements with enterprise customers: assess their data, define training strategies, design reward signals and verifiers, prepare datasets, run training loops, and evaluate results against customer-specific benchmarks.

• Design and build RL training environments for model adaptation, including synthetic data generation pipelines, reward model training, and preference data collection workflows.

• Design and build evaluation infrastructure: define what "better" means for each customer use case, build eval harnesses, curate test sets, and establish baselines that measure real-world performance.

• Own the data pipeline from raw customer data through training-ready datasets, including synthetic data generation, data quality inspection, cleaning, and format standardization.

• Deploy post-trained models across hybrid environments (public cloud, VPC, and on-premises), working with infrastructure teams to ensure inference performance, cost efficiency, and reliability at scale.

• Shape and scale the post-training and evaluation practice by defining playbooks, best practices, and technical standards. Mentor engineers on the team and help define what great applied AI work looks like at Reflection.

What We're Looking For

• Hands-on post-training experience with large language models at scale. You have built and operated RL training environments, designed preference optimization workflows on models at 50B+ parameter scale, and shipped the results to production.

• Experience building synthetic data generation pipelines, reward models, and verifiers for reinforcement learning workflows. You've architected the data and feedback loops that make post-training work.

• Deep understanding of evaluation methodology: how to design evaluations that measure what matters, how to interpret training dynamics, and how to tell the difference between a model that looks good on a benchmark and one that actually works.

• Practical experience with training infrastructure at scale: comfortable working with multi-node GPU clusters, managing large training runs, debugging distributed training, and optimizing for cost.

• Strong software engineering fundamentals. You write production-quality code, not just notebooks. Experience with data pipelines, version control for datasets and models, and reproducible workflows.

• 6+ years of engineering experience, including 2+ years focused on LLM post-training in a leadership capacity (e.g., Tech Lead on a post-training team, Senior MLE owning preference optimization for a product, or Lead Applied Scientist running RL training pipelines in production).

• Experience in customer-facing technical roles, or a genuine interest in developing this skill. In either case, you are comfortable translating domain requirements into training strategies and delivering measurable outcomes.

• Self-starter with high agency and ownership, excelling in fast-paced startup environments where playbooks are still being written.

What We Offer:

We believe that to make intelligence open and accessible to all, you need to start at the foundation. Joining Reflection means building from the ground up as part of a talent-dense team. You will help define our future as a company, and help define the future of open foundational models.

We want you to do the most impactful work of your career with the confidence that you and the people you care about most are supported.

• Top-tier compensation: Salary and equity structured to recognize and retain our talent globally.

• Stock options: Everyone who joins and contributes to Reflection's success gets to share in the upside through stock options.

• Health & wellness: Comprehensive medical, dental, vision, and life, with an annual wellness allowance.

• Meals: Lunch and dinner are provided in the office daily.

• Life & family: 22 weeks paid parental leave for all new birthing and non-birthing parents, including adoptive and surrogate journeys.

• Vacation days: Unlimited paid time off in the U.S. and 30 days in the U.K.

• Sponsorship support: We sponsor visas to help exceptional talent join our team and support long-term immigration pathways where applicable.

• Team building: We have regular off-sites, happy hours, and team celebrations.

Export Control Notice: This position may require access to technology or source code subject to the U.S. Export Administration Regulations. Any offer of employment for this role may be conditioned on the Company's ability to provide the candidate with access to such technology or source code in compliance with applicable U.S. export control laws, which may require the Company to seek government authorization.