Snorkel AI Logo
Snorkel AI· Hauptsitz in Redwood City, California

Research Scientist - RL Training

Ort: New York City, NY (Hybrid); San Francisco, CA (Hybrid); United States (Remote) · Bereich: Data, AI & Analytics · Level: Senior · Veröffentlicht: 29. Mai 2026 · Geprüft: 16. Nov. 2026

Rollenübersicht & Beschreibung

This research scientist role focuses on advancing reinforcement learning (RL) training methodologies for frontier AI models. The scientist will research and implement novel RL algorithms, including RLHF and scalable training techniques, to improve model performance and alignment.
Hiring Telemetrie · Expansions-Signal

Team-Wachstum & Marktbewegung von Snorkel AI beobachten

Polaris7 erfasst offene Vakanzen, strategische Marktbewegungen und M&A-Signale aus verifizierten Primärquellen. Erhalte strukturierte Watchlist-Briefings zu Snorkel AI und vergleiche das Ökosystem mit direkten Wettbewerbern.

Quellenhinweis & Transparenz: Diese Position wurde direkt über das öffentlich zugängliche Karriereportal von Snorkel AI erfasst. Maßgeblich sind die Angaben auf der Original-Stellenausschreibung des Arbeitgebers. Polaris7 erhebt keine Vermittlungsgebühren und führt kein Bewerber-Screening durch.
UnternehmensanalyseProfil aktiv
Snorkel AI Logo

Snorkel AI

snorkel.ai

Unternehmensplattform für datenzentrierte KI-Entwicklung und -Bereitstellung.

Hauptsitz: Redwood City, California

Ähnliche Positionen im DACH-Ökosystem

Verwandte Rollen und Profile aus dem AdTech-, Media- und Datenmarkt

Prüfung geplantSan FranciscoData, AI & AnalyticsSenior

This role focuses on advancing reinforcement learning techniques for training and aligning large language models. The researcher/engineer will develop novel RL algorithms, optimize reward modeling, and improve sample efficiency. Key challenges include stability in large-scale training and ensuring alignment with human intent.

Veröffentlicht 16. Okt. 2026
Prüfung geplantSan FranciscoData, AI & AnalyticsSenior

This role focuses on forward-deployed reinforcement learning, applying RL algorithms to real-world problems in customer environments. The researcher will work closely with clients to implement and fine-tune RL models for specific use cases. Key challenges include adapting RL to production settings, ensuring sample efficiency, and integrating with existing systems.

Veröffentlicht 19. Okt. 2026
Prüfung geplantSan FranciscoData, AI & AnalyticsSenior

This Research Engineer role on the RL Research & Environments team focuses on post-training model capabilities, designing and operating data, evaluation, and environment systems. The role involves building post-training datasets using synthetic generation and self-play, implementing filtering and scoring strategies, and designing reward signals for targeted capability improvements. Strong software engineering fundamentals and experience with large-scale data or ML systems are required.

Veröffentlicht 8. Nov. 2024
Prüfung geplantSan FranciscoEngineering & SoftwareentwicklungSenior

This Research Engineer role focuses on RL infrastructure at Prime Intellect, building the systems that power large-scale reinforcement learning experiments. The engineer will develop scalable training loops, environment orchestration, and data pipelines for RL workloads. Key challenges include managing distributed compute, ensuring reproducibility, and optimizing resource utilization.

Veröffentlicht 8. Juli 2026

Weitere Positionen bei Snorkel AI

3 weitere offene Stellen

Vor 2 Tagen verifiziertNew York City, NY (Hybrid); San Francisco, CA (Hybrid); United States (Remote)RemoteData, AI & AnalyticsSeniorUSD200,000 – USD340,000

This role focuses on red-teaming frontier AI benchmarks to identify weaknesses such as reward hacking, grader failures, and task ambiguity. The researcher will develop and validate fixes, create reusable methods for benchmark quality improvement, and collaborate with benchmark authors to publish improved versions. Requires strong Python skills, experience with LLM/agent evaluation, and a research or engineering background in machine learning.

Veröffentlicht 13. Nov. 2026
Vor 2 Tagen verifiziertNew York City, NY (Hybrid); San Francisco, CA (Hybrid); United States (Remote)RemoteData, AI & AnalyticsLead

This research lead role heads the Open Benchmarks Grants program, providing technical direction and oversight for the development of open benchmarks. The lead will define research priorities, guide grant recipients, and ensure the benchmarks are rigorous, relevant, and impactful for the AI field.

Veröffentlicht 2. Nov. 2026
Vor 2 Tagen verifiziertSan Francisco, CA (Hybrid)Engineering & SoftwareentwicklungSeniorUSD208,000 – USD315,000

This role focuses on building backend product capabilities for Snorkel's AI data platform, including data cataloging, agent benchmarking, and workflow automation. The engineer will own features from concept to production, working closely with Product and Design teams. Strong backend engineering fundamentals are required, with experience in Python or other languages like Java, Go, or Rust.

Veröffentlicht 27. Okt. 2026

Starte mit einem Unternehmen oder Markt. Verfolge, was sich ändert.

Erstelle deinen Polaris7 Workspace, um erweiterte Company Profiles zu nutzen, relevante Akteure in Watchlists zu strukturieren und fokussierte Briefings bei Veränderungen zu erhalten.