Responsibilities
Lead post-training of our LLMs across the full pipeline: continuous pre-training, SFT, and reinforcement learning, with RL as the primary focus (e.g., RLHF, PPO, GRPO, DPO, and related methods).
Design, build, and curate the data that drives each training stage — instruction/SFT datasets, preference pairs, reward signals, on-policy rollouts, and rejection-sampled completions — and define data-preparation strategies tailored to specific business needs.
Partner closely with business and product stakeholders to understand their scenarios, rapidly convert requirements into training plans, and deliver targeted model capabilities on tight timelines.
Run large-scale training on mid-to-large GPU clusters, applying distributed-training techniques (data parallelism, FSDP, and where relevant tensor/pipeline parallelism) and tuning for throughput and stability.
Build and maintain evaluation and reward/verifier pipelines to measure model quality, prevent regressions, and ensure training–serving consistency.
Stay current with post-training research and turn promising techniques into working, production-ready code.
Requirements
Hands-on LLM post-training experience. You have personally run CPT, SFT, and RL training — with demonstrated, practical RL experience (RLHF / PPO / GRPO / DPO or similar), beyond just launching training scripts.
Strong data engineering for ML. You can independently design data-preparation plans for a given business scenario — sourcing, cleaning, filtering, labeling strategy, and synthetic/preference data generation — to meet specific product requirements.
Proven large-scale GPU training ability. You have trained LLMs on mid-to-large GPU hardware and are comfortable with distributed training and debugging at scale.
Strong PyTorch fundamentals; working familiarity with frameworks such as Hugging Face TRL/Accelerate, DeepSpeed or FSDP, and inference engines like vLLM.
Solid understanding of tokenization, attention, chat templates, and common failure modes in alignment/agent training.
A bias toward fast iteration and business impact, with strong communication skills to work across research and product teams.
Preferred Qualifications
Experience designing reward models or rule-based verifiers for RL.
Experience with tool-use / agentic model training (function calling, multi-step planning).
Publications or open-source contributions in LLM post-training or RL.
Benefits
We offer a competitive benefits package
Health, dental, and vision care for you and your family (100% coverage for employee)
Top-tier 401(K) plan with company matching
Paid time off and paid holidays
FSA, HSA and commuter benefits programs
Team activity budget
The US base salary range for this full-time position is listed below. Pay may vary based on a number of factors including job-related skills, level, experience, geographic location and relevant education or training. At NewsBreak, we design our overall rewards package to attract top talents. Depending on the position, the role may also be eligible for discretionary bonus and options. Your recruiter can share more details during the hiring process.
Annual Base Pay Range
$150,000—$230,000 USD
CPRA Privacy Notice for California Candidates
