AI Researcher - Post-Training

Sonar Source
Geneva
Workplace: OnsiteFull timeFunction: Research & Scientific (R&D)Experience: 4+ yearsEducation: mastersSkills: ["Communication","Explaining complex topics","Outcome-driven development","Research translation","Collaboration"]

Research and develop next-generation large language model post-training techniques to power enterprise-grade coding agents. Leverage expertise in static analysis and ML post-training to build practical, high-impact prototypes and translate them into production products. Collaborate with researchers, research engineers, MLOps, and engineers to design experiments, iterate quickly, and drive research toward deployable capabilities for agentic coding workflows.

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

Research and develop next-generation large language model post-training techniques to power enterprise-grade coding agents. Leverage expertise in static analysis and ML post-training to build practical, high-impact prototypes and translate them into production products. Collaborate with researchers, research engineers, MLOps, and engineers to design experiments, iterate quickly, and drive research toward deployable capabilities for agentic coding workflows.
Location: Geneva
Workplace: Onsite
Employment Type: Full time
Job Function: Research & Scientific (R&D)
Seniority: Mid level

Key Responsibilities

  • •Innovate and develop next-generation solutions for enterprise-grade coding agents and models using static analysis plus LLM post-training techniques.
  • •Design hypotheses and experiments, iterate proofs-of-concept quickly, and develop prototypes into cutting-edge products.
  • •Collaborate closely with researchers, research engineers, MLOps, and engineers to translate research into product outcomes.
  • •Drive research and innovation by staying up to date with the latest LLM and agentic developments and sharing knowledge across technical and non-technical audiences.
  • •Contribute as a subject matter expert within a cross-disciplinary team focused on coding model post-training for enterprises.

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, with a solid understanding of modern software engineering practices and tools.
  • •Fluency with Python and experience with core ML frameworks; experience with Rust or SonarQube flagship languages (C#, C++, JS/TS, Java) is a plus.
  • •Expertise in large language model post-training, including policy optimization algorithms (e.g., GRPO, PPO), verifier-based RL (RLVR), supervised fine-tuning (SFT), synthetic data and curation, PEFT, and preference/safety alignment.
  • •Experience driving research projects from findings and prototypes to products, with strong communication skills in English.
Experience:4+ yearsMachine learningLLMsAgentic codingStatic analysisPost-training
Education:Master's in Computer Science, Machine Learning, or a related quantitative field
Skills:CommunicationExplaining complex topicsOutcome-driven developmentResearch translationCollaboration
Languages:English
Tech Stack:PythonRustC#C++JavaJS/TSGRPOPPORLVRSupervised fine-tuning (SFT)Synthetic dataPEFTStatic analysisMLOpsPreference and Safety Alignment

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