NewsBreak
Technology
MachineLearningEngineer,LLMPost-Training
Neural analysis suggests this role is
optimal for Mid+ candidates.
“Machine Learning Engineer, LLM Post-Training at NewsBreak. Skills: LLM Post-Training, Reinforcement Learning, Data Engineering, Large-scale GPU training. Lead post-training of LLMs. Design data for training stages”
What You'll Achieve.
Ship model improvements quickly; Deliver targeted model capabilities
Industry & Context.
Solving meaningful challenges
What They're Looking For.
Must Have
Hands-on LLM post-training experience, Demonstrated practical RL experience, Independently design data-preparation plans, Trained LLMs on mid-to-large GPU hardware, Comfortable with distributed training, PyTorch working familiarity, Solid understanding of tokenization, Solid understanding of attention, Solid understanding of chat templates, Solid understanding of common failure modes
Nice to Have
Experience designing reward models, Experience designing rule-based verifiers, Experience with tool-use training, Experience with agentic model training, Publications in LLM post-training, Publications in RL, Open-source contributions in LLM post-training, Open-source contributions in RL
What You'll Do.
Lead post-training of LLMs
Design data for training stages
Build data for training stages
Curate data for training stages
Define data-preparation strategies
Partner with business stakeholders
Partner with product stakeholders
Understand business scenarios
Convert requirements into training plans
Deliver targeted model capabilities
Run large-scale training
Apply distributed-training techniques
Build evaluation pipelines
Build reward pipelines
Build verifier pipelines
Measure model quality
Prevent model regressions
Ensure training–serving consistency
Stay current with research
Turn techniques into code
How You'll Work.
Team & Collaboration
Work with product teams; Work with business teams; Work across research teams; Work across product teams
Communication Scope
Communication skills
Process & Methodology
Fast iteration
Full Job Description
About NewsBreak Founded in 2015, NewsBreak is the Content Intelligence platform shaping the future content economy. With over 40 million monthly active users, our flagship platform delivers highly personalized local news and information powered by advanced AI, recommendation systems, and adtech. Recognized by Fast Company as #32 on the Top Workplaces for Innovators, we're proud to be Great Place to Work® certified and home to a dynamic team of technologists, product innovators, and business leaders who are passionate about solving meaningful challenges at scale. Together, we reached unicorn status in 2021, and we remain committed to continuing this high-growth trajectory with the right team to fulfill our mission: building the infrastructure layer for content intelligence. If you’re inspired to dream big, innovate fast, and make a difference, we’d love to hear from you! For more information, visit www.newsbreak.com/about About the Role We are looking for a hands-on Machine Learning Engineer to drive the post-training of our large language models, with a strong emphasis on reinforcement learning (RL). You will own the full post-training stack — continuous pre-training (CPT), supervised fine-tuning (SFT), and RL — along with the data preparation that powers it. Just as important, you will work directly with product and business teams to translate real-world use cases into concrete training objectives and ship model improvements quickly. This is a high-ownership role for someone who has actually trained models, not just read about it. 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 tailor
Applying for this Machine Learning Engineer, LLM Post-Training role?
Most applicants get filtered before a human reads their resume. See if yours makes the cut.
How to Apply on Greenhouse
- Create a Greenhouse profile before applying — it saves time across multiple applications.
- Upload your resume as a PDF; the parser handles it better than Word.
- Answer all knockout questions carefully — wrong answers auto-reject before a human sees you.
- Enable email notifications to track application status in real time.
ANONYMOUS · UNFILTERED
What do employees actually say about NewsBreak?
Real rants from real employees. Read before you apply.