Skip to content
pushkal.

Seattle, WA

Pushkal Kumar

AI Researcher. Software Engineer. Founder.

Building intelligent systems that solve real-world problems.

  • Retrieval-Augmented Generation Security
  • Computational Biology
  • AI Infrastructure
  • Developer Tools
  • Startup Building
View Projects Read Research Resume

By the numbers

Track record

0
Research Papers Accepted
0
Patent Pending
0+
AI Systems Built
0+
GitHub Repositories
0
SAT
0
GPA
0+
DECA Members Led
$0k+
Budget Managed
0+
Public Speeches

Selected work

Featured projects

All projects

VALOR-RAG

Patent PendingHICSS Submission

Trust-scored retrieval defense for RAG pipelines

A security layer for retrieval-augmented generation that assigns dynamic trust scores to retrieved documents, detects corpus poisoning, and adapts its thresholds as attack patterns shift. Developed in collaboration with Washington State University.

  • Dynamic trust scoring over retrieved documents at query time
  • Poison detection that flags adversarial insertions before generation
  • Adaptive thresholds tuned against evolving attack distributions

Architecture

  1. Retrieval

    Vector store query with candidate document set

  2. Trust Scoring

    Per-document trust signal from provenance, consistency, and semantic drift

  3. Poison Detection

    Adversarial pattern classifier over candidate contexts

  4. Adaptive Gate

    Threshold policy that admits or quarantines documents

  5. Generation

    LLM generates only from admitted, trust-weighted context

Python · PyTorch · Transformers · Vector Databases

Meridian

Founder

Operational infrastructure for tutoring businesses

A multi-tenant CRM platform built for session-based education businesses. Generic CRMs model deals; tutoring businesses run on recurring sessions, parent communication, and per-student billing — Meridian models that directly.

  • Authentication and role-based access control across tenants
  • Workflow automation for scheduling, reminders, and follow-ups
  • Notifications and analytics tuned to session-based revenue
  • Multi-tenant architecture with per-org data isolation

Next.js · TypeScript · FastAPI · PostgreSQL

RAGuard

Open-source RAG security toolkit

Prompt-injection and retrieval-attack detection for RAG applications. Ships as a drop-in middleware layer: score incoming queries and retrieved contexts, block or flag adversarial patterns before they reach the model.

  • Prompt injection detection across common attack categories
  • Retrieval-context screening before generation
  • Drop-in FastAPI middleware integration

Python · Transformers · FastAPI

Context Bridge

Persistent memory for Claude Code

A checkpointing and context-restoration system for AI coding agents. Records goals, decisions, blockers, and attempt history across sessions so an agent resumes exactly where it left off instead of rediscovering state.

  • Session checkpointing with goals, blockers, and decisions
  • Cross-session context restoration on startup
  • Stagnation detection and attempt-replay to prevent repeated failures

Python · FastAPI · SQLite

Publications

Research

All research
NeurIPS WorkshopAccepted2025

Temporal Transformers for Representation Learning in Computational Biology

Applies temporal transformer architectures to biological sequence data, learning representations that capture time-dependent structure standard encoders miss.

AAAI WorkshopAccepted2025

Foundation Model Representations for Biological Sequence Analysis

Evaluates how foundation-model embeddings transfer to computational biology tasks, and where domain-specific fine-tuning is still required.

ACLUnder Review2026

Representation Learning Under Distribution Shift

Studies how learned representations degrade when deployment data drifts from training data, with implications for model reliability.

Open source

GitHub activity

Profile

Get in touch

Let's build something

I'm always interested in research collaborations, ambitious projects, and conversations about AI security and infrastructure.

Contact me