
A gateway that routes each prompt to the model tier the task actually needs.
Department metadata, context-window heuristics, and an in-house complexity classifier cut average inference cost by 27%.
AI Engineer, PurpleMerit, 2026
Agentic systems, training runs, and research.

Department metadata, context-window heuristics, and an in-house complexity classifier cut average inference cost by 27%.
AI Engineer, PurpleMerit, 2026

Fine-tuning Qwen 2.5 Coder 1.5B on cached telemetry cut inference latency by 11x and token cost by 96%.
SDE-1 AI, ZysecAI, 2025

Trained on TinyStories with FlashAttention, bf16, and tensor parallelism. Throughput rose from 14k to 41k tokens/s, and validation loss landed at 1.1.
Independent, 2025

Progressive distillation kept PSNR, SSIM, CNR, and lesion-detection sensitivity roughly in place while cutting inference time.
Research Intern, Samsung R&D, 2023
Open to research, inference work, and teams building agentic systems. Reach out.