SAM SANKAR P

• Designed, built, and deployed three open-source AI systems across agent tooling, LLM evaluation, and multimodal fine-tuning.
• Managed architecture, model training, containerized deployment, and technical documentation.

• Delivered a bulk certificate-generation application using React, JavaScript, Node.js, and PHP.
• Completed requirements, implementation, testing, debugging, and handoff inside the sprint.

A local-first MCP bridge that lets AI agents inspect, create, validate, and export procedural material graphs.

143 typed MCP tools · 392 node definitions · 4 permission modes

An OpenEnv-compatible training and evaluation environment for factual grounding, citation discipline, calibration, and refusal behavior.

1,090,163 evaluation examples · 38 datasets · 9 reward components

An interpretable deepfake-analysis pipeline using staged visual reasoning, self-critique, and contradiction-aware evidence aggregation.

3 reasoning stages · SFT + GRPO published adapters · 4-bit GGUF variant

A schema-driven application generator that converts database structure into a functional initial interface without requiring a natural-language prompt.

0 required prompts · 3 core passes