AI Product · Data Systems · Enterprise AI

MOKSHITHBUILDS AI.

Product-minded AI systems builder focused on production RAG, agentic workflows, LLMOps evaluation, and data products that move retention, cost, latency, and risk metrics.

Risk Impact

$300M+ surfaced

Automation

500+ tickets / week

Growth

6x engagement lift

Competitive AI Portfolio Systems

001 — 007
Production RAG Contract Intelligence
01Query Routing · Re-Ranking

Production RAG Contract Intelligence

Hybrid RAG + relational search over 1,000+ supplier contracts, designed with query rewriting, source routing, sub-query decomposition, and re-ranking to surface liability without hallucinating in high-stakes decisions.

LangGraphpgvectorBGE RerankerSQL
EchoMind Agentic RevOps Engine
02Graph Orchestration

EchoMind Agentic RevOps Engine

Multi-agent content workflow for GTM teams: scraper, grader, RAG validator, LLM generator, and QA loop with stateful handoffs to raise content pass rate toward 85% while controlling hallucination risk.

LangGraphPRAWVector DBGA4 / GSC
LLMOps Guardrail Evaluation Pipeline
03Reliability · Safety

LLMOps Guardrail Evaluation Pipeline

CI-style evaluation layer for RAG and agent systems: malicious-prompt stress tests, faithfulness scoring, answer relevance, context precision, and dashboard exports so model behavior is tested like production software.

RagasTruLensNeMo GuardrailsW&B
Local Fine-Tuning Optimization Lab
04QLoRA · Quantization

Local Fine-Tuning Optimization Lab

Build track for privacy-sensitive domain models: fine-tune Llama or Mistral on niche documentation with QLoRA, track loss and GPU memory, then quantize to 4-bit for low-latency local inference.

PyTorchTransformersUnslothllama.cpp
Vantage Point — VC Investment Intelligence
05Thesis Generation · ML Prediction

Vantage Point — VC Investment Intelligence

Streamlit investment intelligence dashboard that turns historical VC data into thesis-ready insights—exit efficiency, geographic capital density, sector deep dives, investor matchmaking, and a Random Forest startup success predictor.

StreamlitPythonscikit-learnPandasLive demo
GridPulse ML — EV Surge Risk Pipeline
06MLOps · CI/CD · Serving

GridPulse ML — EV Surge Risk Pipeline

End-to-end production ML system that predicts EV charging station surge risk: reproducible data prep, shared feature engineering, validation gates, drift monitoring, FastAPI inference with Prometheus metrics, Docker, and GitHub Actions CI/CD—runnable with no external datasets or cloud accounts.

FastAPIscikit-learnDockerGitHub Actions
ChatGPT Review Topic Intelligence
07LDA · NMF · MLflow

ChatGPT Review Topic Intelligence

Streamlit app for large-scale ChatGPT app review analysis: upload a CSV, run LDA and NMF topic models, view aggregated theme distributions, and export predictions—with models trained in Colab and tracked in Databricks MLflow.

Streamlitscikit-learnMLflowLDA / NMFLive demo
What I Build With

Production AI disciplines.

Query Routing · Re-Ranking

Production RAG

Hybrid retrieval with sub-query decomposition, BM25+vector fusion, and BGE re-ranking. Built to surface facts without hallucinating on high-stakes decisions.

LangGraph · CrewAI

Agentic Orchestration

Stateful multi-agent pipelines with typed handoffs, human-in-the-loop checkpoints, and graceful fallbacks.

Ragas · TruLens · W&B

LLMOps Evaluation

CI-style eval harness: faithfulness, context precision, answer relevance, malicious-prompt stress testing, and drift monitoring.

SQL · Snowflake · BI

Data Products

Executive decision dashboards, risk-scoring pipelines, and dbt data models that power $300M+ in liability visibility.

QLoRA · Quantization

Model Optimization

Fine-tune Llama/Mistral on proprietary docs with QLoRA, then quantize to 4-bit for sub-100ms local inference.

PostHog · GA4 · Mixpanel

Product Analytics

Behavioral cohort analysis, funnel modeling, and LLM-assisted VoC analysis over 1M+ app reviews.

Core Expertise

RAG & Query TransformationRouter / Re-ranker
Agentic OrchestrationLangGraph / CrewAI
LLMOps EvaluationRagas / TruLens
Product AnalyticsPostHog / GA4
Data ProductsSQL / Snowflake / BI
Model OptimizationQLoRA / Unsloth
"I build AI products where model behavior is measured against business outcomes: liability exposure, support latency, engagement lift, and hallucination risk."

AI that can't be measured doesn't survive production — evaluation and business metrics come first, benchmarks second.

— Product + AI Systems Operating Principle

Trajectory

Product judgment
with AI systems depth.

Mokshith Kumar builds at the intersection of product strategy, data systems, and applied AI. His work spans enterprise contract intelligence, supplier automation, AI-driven lifecycle messaging, hybrid RAG support, agentic RevOps, and large-scale voice-of-customer analysis over roughly one million app reviews.

  1. 2025

    MS Artificial Intelligence in Business

    Arizona State University · W. P. Carey

  2. 2024

    Product Manager, Founding Member

    Blip · AI notifications, RAG support, retention analytics

  3. 2023

    Associate Product Manager

    Cisco · contract intelligence, supplier workflows, $300M+ liability visibility

  4. 2022

    Business Analyst

    Cisco · Snowflake dashboards, risk scoring, executive decision systems

Open To Competitive AI Roles

Build systems
that ship.

Targeting AI Product Manager, AI Application Developer, and Full-Stack AI Engineer roles where product sense and production AI depth both matter.

Contact Mokshith
San Jose / PhoenixEnterprise AIStartups