Skip to content
View suniljavadi's full-sized avatar

Block or report suniljavadi

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
suniljavadi/README.md

Sunil Javadi

AI / GenAI Engineer · Data Engineering Foundation

Grounded AI systems | Safe data access | Evaluation-first delivery

Portfolio · LinkedIn · Resume · Email

Python SQL FastAPI Streamlit Docker Evaluation first Production minded

I build AI applications where the model is one component of a larger, testable system. My work connects data engineering fundamentals with RAG, Text-to-SQL, workflow automation, operational analysis, and deployment validation.

Selected Engineering Projects

Project What it demonstrates Evidence Links
Safe Text-to-SQL Schema and KPI context, SQL policy validation, bounded read-only execution 10 tests; synthetic evaluator: 90% execution, 80% semantic correctness App · Code
Enterprise RAG Knowledge Assistant Grounded retrieval, document context, source-aware answers, and enterprise knowledge workflows Architecture and retrieval behavior documented Code
Meeting Notes Structured extraction, reviewable drafts, approval before communication 11 tests; public health endpoint reachable API · Code
AI Log Analyzer Parsing, incident retrieval, evidence, hypotheses, confidence, action gates 6 local tests; deployable, not publicly hosted Code

How I Build AI Systems

01 · Ground 02 · Guard 03 · Measure
Retrieve schemas, documents, metrics, or source notes before generation. Validate model output, restrict tools, use least privilege, and gate external actions. Track correctness, groundedness, safety, latency, cost, and recovery behavior.

Grounded AI Safe execution Observable delivery

What Each Project Teaches

Project Core lesson Production question
Text-to-SQL Valid SQL is not automatically correct SQL. How do we protect the database and verify business meaning?
Enterprise RAG Fluent answers need current, authorized evidence. Was the right context retrieved, and can the answer be supported?
Meeting Notes Structured extraction is safer than opaque rewriting. What prevents invented commitments or an incorrect recipient?
AI Log Analyzer Diagnosis should expose evidence and uncertainty. How does an engineer verify the hypothesis before acting?

My Engineering Thesis

A useful AI feature needs more than a model call. It needs trustworthy data, explicit contracts, validation at system boundaries, safe failure behavior, measurable quality, and an owner when something goes wrong.

In practice

  • Grounding: retrieve schemas, documents, metrics, or source notes before generation.
  • Safety: treat generated SQL, tools, and external actions as untrusted until authorized.
  • Evaluation: separate correctness, groundedness, safety, latency, cost, and availability.
  • Operations: distinguish health checks, smoke tests, local tests, and semantic evaluation.
  • Data: carry meaning, freshness, lineage, and access scope into the AI workflow.
Evidence and status definitions
Label Meaning
Reachable A public page or endpoint responded successfully.
Smoke tested A representative hosted interaction completed.
Locally validated Tests or compilation passed in the recorded environment.
Deployable Deployment configuration exists, but a current public check is not claimed.

These labels are intentionally narrower than “production-ready.” A URL, a passing test suite, and a successful model response each prove different things.

Technology

Python · SQL · FastAPI · Streamlit · PostgreSQL · SQLite · SQLAlchemy · Pydantic · sqlglot · LangChain · FAISS · Docker · pytest

Current Learning Focus

Evaluation datasets · RAG freshness · SQL safety · AI observability · deployment contracts · incident debugging · human approval workflows

From Data to AI

SQL / ETL / BI  →  Data Engineering  →  Python  →  ML
									  →  LLM Apps / RAG
									  →  Safe Agents / Evaluation

Other Work

Streamlit Chatbot · RAG Q&A Demo · Machine Learning · Deep Learning · SQL Practice · Power BI

Pinned Loading

  1. Text-to-SQL-AI-Agent Text-to-SQL-AI-Agent Public

    Enterprise-style Text-to-SQL agent with schema-aware retrieval, SQL validation, bounded execution, FastAPI, Streamlit, and evaluation.

    Python 1

  2. AI-Log-Analyzer-RCA-Agent AI-Log-Analyzer-RCA-Agent Public

    Synthetic-data AI log analyzer for SQL, SSIS, ETL, and application failures with incident retrieval and structured root-cause analysis.

    Python 1

  3. Enterprise-RAG-Confluence-Knowledge-Assistant Enterprise-RAG-Confluence-Knowledge-Assistant Public

    Synthetic enterprise RAG assistant with hybrid retrieval, reranking, citations, role-aware filtering, FastAPI, and Streamlit.

    Python

  4. AI-Agent-Jira-Integration AI-Agent-Jira-Integration Public

    Mock-first AI engineering assistant with validated Jira tools, approval gates, policy retrieval, audit events, FastAPI, and Streamlit.

    Python 1

  5. AI-SQL-Optimizer AI-SQL-Optimizer Public

    Safety-first SQL analysis assistant using SQLGlot parsing, tuning rules, constrained rewrites, FastAPI, Streamlit, and PostgreSQL-shaped data.

    Python 1

  6. Enterprise-RAG-Meeting-Intelligence-Agent Enterprise-RAG-Meeting-Intelligence-Agent Public

    Synthetic document and meeting intelligence system with section-aware ingestion, hybrid retrieval, citations, and structured meeting extraction.

    Python 1