AI Research Engineer, Post-Training
Stockholm, LondonFull-timePosted 5mo ago
About the role
Lovable seeks an engineer with hands-on post-training experience at scale to own the full post-training pipeline, translating research into production training recipes for code generation and agent workloads, with a focus on shipping fast to users.
Responsibilities
- Own the full lifecycle of Lovable's post-training pipeline - from data curation and training runs through evaluation and deployment
- Apply and adapt reinforcement learning, preference optimization, and supervised fine-tuning methods to improve models for code generation, intent understanding, and agent reliability
- Build evaluation and experimentation infrastructure to measure real-world impact across helpfulness, safety, latency, and reliability
- Develop and operate production systems that run training jobs at scale, including GPU orchestration and data pipelines
- Collaborate with agent, product, and infrastructure engineers to turn model gains into user-facing product improvements
- Investigate and resolve failures end-to-end - root cause analysis across training recipes, data, or serving
- Read papers, run experiments, and move fast to get promising research into production within days or weeks
Qualifications
- You've personally run post-training jobs on large language models - RFT/RLVR, preference optimization, or similar
- Solid production coding ability; systems must run reliably
- Fluent in at least one major ML framework (PyTorch, JAX) and comfortable with distributed training and GPU clusters
- Understanding of the math behind preference optimization, reward modeling, and alignment techniques
- Experience building or contributing to evaluation systems that capture real-world quality beyond benchmarks
- Ability to trace model quality regressions from user-facing symptoms through serving, inference, and training
- Desire to ship and bias toward delivering user-facing impact
Skills
Required:Post-training at scaleProduction software engineeringDistributed training and GPU clustersReinforcement learning / Preference optimization / Supervised fine-tuningEvaluation systems design
Last updated Sep 9, 2026. Interested? Apply on the company site.
About Lovable
Build something
Build software products, using only a chat interface
ai coderai developerai engineerai full stack engineerai software engineerai web agencyai website builderai-infrastructure-and-development
More open roles at Lovable
- Partner Operations Manager4d agoStockholm · GTM
- Technical Writer1w agoStockholm · EPD
- Data Infrastructure Engineer1w agoStockholm, London · EPD
- Growth Engineer1w agoLondon · EPD
- Marketing Growth Engineer2w agoLondon · EPD