Staff Research Scientist – Reinforcement Learning

Job not on LinkedIn

πŸ•’ July 3

Where this job comes from

Posted on Centific's careers page β†—Centific's careers page, not through a job board

First seen by Remote Rocketship July 3

Still open on Centific's site. Checked 6 hours ago.

Apply Now
Logo of Centific

Centific

5001 - 10000 employees

πŸ€– Artificial Intelligence

πŸ›οΈ eCommerce

🏒 Enterprise

Artificial Intelligence β€’ eCommerce β€’ Enterprise

Centific is a company that provides Zero distance innovationβ„’ solutions for Generative AI (GenAI) creators and industries. The company focuses on rapid, safe, and scalable AI deployment, offering high-quality data and models to drive business impact through accelerated deployments. With expertise in AI and data science, Centific is positioned as a leader in data annotation and labeling for AI/ML, recognized by the Everest Group’s 2024 assessments. Their AI platforms support enterprise-ready applications, particularly improving search, personalization, fraud detection, and customer engagement in ecommerce environments. Centific serves a wide array of industries with foundational and frontier AI data solutions, fostering partnerships with leading model providers to advance sustainable GenAI models and applications.

πŸ“‹ Description

β€’ Design simulation environments and digital twins for enterprise workflows β€’ Post-train LLM agents using RLHF, DPO, GRPO, PPO, and emerging methods β€’ Build pipelines that convert human-labeled traces and verifiable signals into training data β€’ Architect multi-turn, tool-using agents with closed learning loops β€’ Design reward functions and verifiers that resist reward hacking and reflect real task outcomes β€’ Set the technical bar across the team β€” architecture, code review, engineering standards β€’ Mentor researchers and engineers; drive technical direction through influence β€’ Translate research into production; contribute to publications

🎯 Requirements

β€’ 7+ years in ML/AI research or engineering; 3+ years at senior/staff level β€’ MS or PhD in Computer Science, Machine Learning, or related field (or equivalent) β€’ 5+ years hands-on RL β€” environment design, reward engineering, policy optimization β€” with at least one production deployment LLM Post-Training β€’ 3+ years fine-tuning LLMs with hands-on RL post-training (RLHF, DPO, GRPO, PPO) β€’ Expert-level implementation of RLHF pipelines, reward modeling (Bradley-Terry), DPO, and KTO β€’ Strong Python and software engineering skills β€” comfortable building production pipelines, not just notebooks β€’ Deep expertise in MDPs, policy gradient methods (PPO, SAC), and temporal difference learning β€’ Working knowledge of modern post-training and rollout-serving libraries (TRL, veRL, OpenRLHF, SkyRL)

πŸ–οΈ Benefits

β€’ Health insurance β€’ 401(k) matching β€’ Flexible work hours β€’ Paid time off β€’ Remote work options

Apply Now

πŸ“Š Check your resume score for this job

Improve your chances of getting an interview by checking your resume score before you apply.

Similar Jobs

πŸ•’ June 27

Netflix

10,000+ employees

πŸ“± Media

πŸ‘₯ B2C

Research Scientist designing machine learning and optimization algorithms for Netflix’s ad marketplace. Improving auctions, pricing, experimentation, and advertiser outcomes.

πŸ•’ June 24

GiveWell

51 - 200

🀲 Charity

🀝 Non-profit

🌍 Social Impact

Senior New Areas Researcher at GiveWell directing funding towards cost-effective interventions. Leading research agendas and answering complex questions to inform grantmaking decisions.

πŸ•’ June 18

KoBold Metals

51 - 200

πŸ€– Artificial Intelligence

πŸ”¬ Science

⚑ Energy

Applied Scientist at KoBold Metals developing instruments and models for mineral exploration using AI and data tools. Collaborating with geoscientists and engineers to drive discovery.

πŸ•’ June 8

Foundation EGI

11 - 50

🏭 Manufacturing

πŸ’Ό Consulting

πŸ“¦ Logistics

Research Scientist developing AI-driven solutions for engineering applications in a fast-paced startup. Leveraging advanced technologies to enhance design and manufacturing processes.

πŸ•’ May 31

adaption

1 - 10

πŸ’Ό Consulting

πŸ“¦ Logistics

πŸ“£ Marketing

Senior Research Scientist focused on building models that continuously evolve with the world. Collaborating on real-time learning and interface design to enhance intelligent systems.

Built byΒ Lior Neu-ner. I'd love to hear your feedback β€” Get in touch via DM or support@remoterocketship.com
Follow Remote Rocketship on LinkedInFollow Remote Rocketship on InstagramFollow Remote Rocketship on FacebookFollow Remote Rocketship on TikTok