
Senior Software Engineer - Model Training & AI Evals
Lead ownership of end-to-end evaluation and benchmarking infrastructure and domain-specific post-training (SFT, RLHF, RLAIF, DPO) for foundation models. Responsibilities include designing task-level evals, building comparative benchmark pipelines, synthetic data generation, CI-integrated regression suites, dataset curation, and conducting fine-tuning and ablation studies. Requires strong software engineering skills in Python and experience with PyTorch or JAX and distributed training.







