Capstone
Adaptive LLM Inference Engine for Resource-Constrained Systems
A capstone project exploring efficient local LLM inference, model selection, and quantization for constrained environments.
Visual note
A quiet, illustrative setting for the work and study behind the projects.
Two projects, one technical direction.
The work below is drawn only from the facts provided for Santosh M. It keeps the focus on what was actually shared: one capstone and one internship setting.
Internship
CoAI.Pro
Software engineering work on an AI-powered website generation platform, shared here as a real internship setting and not as a broader claim.
Next
Explore the work in context.
If you'd like a broader introduction to Santosh M, the home page brings the identity, study path, and action together in one place.