AI Researcher - Post-Training

Sonar Source
London
Workplace: OnsiteFull timeFunction: Research & Scientific (R&D)Experience: 4+ yearsEducation: mastersSkills: ["Communication","Explaining complex topics","Outcome-driven development","Cross-disciplinary collaboration","Research innovation"]

Work on post-training large language models to power enterprise-grade coding agents. Combine Sonar’s static analysis expertise with state-of-the-art LLM post-training research to develop practical techniques, prototypes, and prototypes-to-product improvements. Collaborate with researchers, research engineers, MLOps, and engineers, stay current on LLM/agentic advances, and communicate complex technical ideas clearly to technical and non-technical audiences.

Loading

Loading job details...

Preparing the role view and application actions.

FursaFursa
Sonar Source
Sonar Source
2 days ago

AI Researcher - Post-Training

✓ Verified Job

Canonical indexed version, validated from employer's careers page.

Source: Company careers pageValidated by: Fursa AI
Last checked: 3 hours agoStatus: Live

Job Summary

Work on post-training large language models to power enterprise-grade coding agents. Combine Sonar’s static analysis expertise with state-of-the-art LLM post-training research to develop practical techniques, prototypes, and prototypes-to-product improvements. Collaborate with researchers, research engineers, MLOps, and engineers, stay current on LLM/agentic advances, and communicate complex technical ideas clearly to technical and non-technical audiences.
Location: London
Workplace: Onsite
Employment Type: Full time
Job Function: Research & Scientific (R&D)
Seniority: Mid level

Key Responsibilities

  • •Develop and innovate enterprise-grade coding agents and models by combining static analysis expertise with LLM post-training techniques.
  • •Drive LLM post-training research and apply methods such as policy optimization, verifier-based RL, supervised fine-tuning, and data-centric approaches.
  • •Translate research prototypes into cutting-edge products through iteration and collaboration with researchers, research engineers, MLOps, and engineers.
  • •Act as a subject-matter expert in a cross-disciplinary team, contributing to next-generation coding model post-training for enterprises.
  • •Stay up to date on LLM and agentic developments and communicate complex technical details to technical and non-technical audiences.

Key Requirements

  • •Advanced academic background (Master’s or PhD) in Computer Science, Machine Learning, or a related quantitative field.
  • •4+ years industry experience in machine learning and modern software engineering practices.
  • •Fluency with Python and core ML frameworks; experience with Rust or SonarQube languages (C#, C++, JS/TS, Java) is a plus.
  • •Expertise in post-training of large language models, including policy optimization (GRPO, PPO), verifier-based RL (RLVR), and supervised fine-tuning (SFT).
  • •Experience driving research projects from prototypes to valuable products and strong communication skills in English.
Experience:4+ yearsMachine learningLarge language modelsLLM post-trainingAgentic software development
Education:Master's in Computer Science, Machine Learning, or a related quantitative field
Skills:CommunicationExplaining complex topicsOutcome-driven developmentCross-disciplinary collaborationResearch innovation
Languages:English
Tech Stack:PythonRustC#C++JS/TSJavaGRPOPPORLVRSFTPEFTSynthetic dataPost-trainingStatic analysis

Company Brief

Sonar Source
Builds static code analysis and continuous inspection tools (SonarQube, SonarCloud, SonarLint) that identify bugs, vulnerabilities, and code smells across multiple languages to help teams improve code quality and maintainability.
Industry: Developer Tools
Company Size: Large (251 to 1,000 employees)
Growth: Established Company
Headquarters: Geneva, Switzerland
Founded: 2008
WebsiteLinkedIn