Agentic tool infrastructure
MaterialPilot
A local-first MCP bridge that lets AI agents inspect, create, validate, and export procedural material graphs.
Open ↗AI systems builtto hold upunder inspection.
I'm Sam Sankar, an AI/ML engineer building practical agent infrastructure, grounded evaluation environments, and research tooling that can be examined end to end.
01 / BASE
Virudhunagar, Tamil Nadu, India
02 / PRACTICE
AI systems engineering
03 / STATUS
Open to focused collaborations
01 / SELECTED SYSTEMS
Works® 25—26
Open-source systems for agentic tooling, model evaluation, and reliable AI delivery—each presented with source evidence.
Open ↗LLM grounding & evaluation
HallucinationGuard-Env
An OpenEnv-compatible training and evaluation environment for factual grounding, citation discipline, calibration, and refusal behavior.
Open ↗Multimodal reasoning
AEGIS
An interpretable deepfake-analysis pipeline using staged visual reasoning, self-critique, and contradiction-aware evidence aggregation.
Open ↗Schema-driven application generation
Promptless Generator
A schema-driven application generator that converts database structure into a functional initial interface without requiring a natural-language prompt.typed MCP tools
node definitions
evaluation examples
datasets
02 / PROFILE
From research prototype to dependable system.
My work connects the experimentation of applied AI with the discipline needed to operate it: typed boundaries, visible evidence, practical deployment paths, and explicit limitations.
The goal is not an impressive demo. It is a system another person can understand, test, and carry forward.
More about the practice ↗03 / CAPABILITY MATRIX
Tools are only useful when the boundaries are clear.
Select a capability to trace how it appears in the published work.
SELECTED CAPABILITYMCP
Used in: MaterialPilot · HallucinationGuard
01 / Model engineering
02 / Agentic systems
03 / Infrastructure
04 / Applied AI
04 / EXPERIENCE TRACE
Independent research, built for real delivery.
INDEPENDENT R&D / MAR—JUL
AI Infrastructure & MLOps Engineer
Built open-source AI systems across architecture, fine-tuning, evaluation, deployment, testing, and documentation.
IT LINKS / INTERNSHIP / 10 DAYS
Full-Stack Web Development Intern
Delivered a bulk certificate-generation application from requirements through testing, debugging, and handoff.
05 / EDUCATION
Bachelor of Engineering
Computer Science and Engineering
AAA College of Engineering and Technology2023—2027 expectedCGPA 7.8 / 10
06 / CERTIFICATION ARCHIVE
Oracle
OCI 2025 Certified AI Foundations Associate
Oracle
OCI 2025 Certified Foundations Associate
NPTEL
GPU Architectures and Programming
NPTEL
CPU Architecture
NPTEL
Industry 4.0 and Industrial Internet of Things
Google Analytics Certification
MongoDB University
Connecting to MongoDB in Node.js
Inspectability
Intermediate evidence stays visible.
Local-first
Authority and data stay close to the user.
Reproducibility
Systems are documented, testable, and repeatable.
Clear limits
Unknowns are named instead of designed away.
07 / START A CONVERSATION