Agentic AI Engineer // USA · open to roles

Tejas
Kumar

I build governed AI systems for regulated industries — banking, healthcare, finance. My operating doctrine: agents advise, deterministic code decides, a human acts. Nine years of shipping ML, NLP, RAG and agentic workflows into production on Azure and AWS.

Explore systems ↓ Get in touch
0
Years shipping AI/ML
0
Regulated industries
0
Production systems
0
Clouds — Azure · AWS
fig.01 // signature system

Anatomy of a governed
agentic workflow.

The deceased-account workflow I built at a major US bank, drawn the way it actually runs: AI Foundry agents write advisories, a deterministic rule makes the call, and every case ends at exactly one human gate. No agent moves money. Tap a node to see its job.

deceased-account workflow · banking operations langgraph × azure ai foundry × n8n
CASE INTAKE
n8n · FastAPI
→
STOP AGENT
advises
→
PROFILE AGENT
advises
→
DECISION RULE
python · decides
→
HUMAN GATE
acts
→
EXECUTE
n8n · audited
tap a node to see what it does here
agent — advisory only human — final authority
profile // 02

Production AI, with the
guardrails built in.

I'm an AI/ML engineer who has spent nine years taking models out of notebooks and into production systems that enterprises actually trust — across banking, healthcare, finance and utilities.

Right now, at Citizens Bank, I design agentic AI for banking operations: LangGraph orchestration, Azure AI Foundry agents, semantic search over enterprise knowledge, and the governance layer around all of it — prompt validation, structured outputs, audit logging, behavior monitoring.

Before that I built RAG and document-intelligence platforms for Cigna, ML services for financial analytics at Deloitte, and NLP systems for Duke Energy at Accenture. The common thread: AI that holds up under regulation, audit and real operational load.

Tejas Kumar — Agentic AI Engineer
LocationUnited States
CurrentlyAgentic AI Engineer
Citizens Bank
FocusAgentic systems · RAG
AI governance · MLOps
EducationM.S. Computers & Info. Science
Southern Arkansas University
Emailtejaskumar2096@gmail.com
LinkedInlinkedin.com/in/actejas
stack // 03

Technology core.

systems // 04

Systems I've shipped.

Banking · Agentic AIsys.01

Deceased-Account Agentic Workflow

An end-to-end agentic banking workflow: n8n intake, LangGraph orchestration, Azure AI Foundry advisory agents, a deterministic decision rule and a mandatory human gate — the pattern drawn in fig.01, proven end to end with monitoring.

LangGraphAzure AI Foundryn8nFastAPIPythonHuman-in-the-Loop
  • Designed the governance doctrine: agents advise, deterministic code decides, a human acts — no agent touches money.
  • Built two advisory Foundry agents (transaction-stop, profile-update) provisioned once via script, invoked from LangGraph.
  • Implemented the single-source-of-truth decision rule flagging uncoded transactions and account-status conflicts.
  • Wired business-readable n8n stages from intake to estate-binder preparation with one merged human-decision node.
  • Exposed the orchestration as a FastAPI service with a clean 5-dependency footprint, ready for Azure Container Apps.
Banking · Retrievalsys.02

Enterprise Semantic Search Platform

Semantic search and RAG over enterprise banking knowledge — vector embeddings, Azure AI Search and retrieval-augmented generation serving intelligent document workflows in a regulated environment.

Azure AI SearchRAGEmbeddingsAzure OpenAILangChainRedis
  • Built semantic retrieval with vector embeddings and Azure AI Search for enterprise knowledge discovery.
  • Implemented governance controls: prompt validation, structured outputs, audit logging, behavior monitoring.
  • Optimized document-intelligence workflows through prompt engineering and retrieval tuning.
  • Deployed as distributed microservices on Docker, Kubernetes and Azure Container Apps.
  • Instrumented with Azure Monitor, Application Insights, LangSmith and LangFuse.
Healthcare · RAGsys.03

Healthcare Knowledge & Document Intelligence

Production AI services for a major health insurer — semantic search, intelligent document processing and predictive analytics, deployed with full MLOps lifecycle management across regulated healthcare systems.

PythonFastAPIPineconeFAISSMLflowKubernetes
  • Built enterprise semantic search with vector embeddings, Pinecone, FAISS and Azure AI Search.
  • Shipped ML models and intelligent search as scalable Python + FastAPI microservices.
  • Implemented AI governance: model validation, documentation, auditability and responsible-AI deployment.
  • Automated deployment pipelines with Docker, Kubernetes, MLflow, GitHub Actions and Azure ML.
  • Improved workflow accuracy via prompt engineering, retrieval optimization and production monitoring.
Desktop tooling · Solo buildsys.04

PDF Editor — Make Any PDF Editable

A desktop application that opens any PDF and makes it directly editable — click-to-edit text overlay, drag-to-create text boxes, and save-through with the original file as the source of truth. Built solo, end to end, with an AI-assisted development workflow.

PythonDesktop GUIPDF engineAutomated tests
  • Click-to-edit overlay on rendered pages plus drag-to-create text boxes anywhere on the document.
  • Save-through pipeline that writes edits back to a valid PDF and preserves page rotation flags.
  • Graceful degradation by design: font look-alike fallback for missing glyphs, shrink-to-fit for overlong text.
  • 51 automated checks across the engine and GUI — load, edit, save, dirty-state and folder handling.
  • Honest limitations documented in the README, including a deliberate no-OCR scope decision.
Utilities · NLP & Predictive MLsys.05

Customer NLP & Predictive Maintenance

Enterprise NLP and ML for a major US utility — complaint classification, intent detection and equipment-failure prediction feeding customer service and maintenance planning across operational systems.

TensorFlowScikit-learnspaCyFlaskAWSDocker
  • Production NLP models for complaint classification, intent detection and text analytics.
  • Predictive models identifying equipment failures to improve maintenance planning and asset reliability.
  • REST APIs integrating ML predictions into enterprise customer-service applications.
  • Automated inference workflows supporting real-time operational decisions.
  • End-to-end pipelines: feature engineering, training, validation, deployment, monitoring.
timeline // 05

Where I've worked.

Aug 2025 — Present
Richmond, VA

Citizens Bank

Agentic AI Engineer
  • Design agentic AI for banking operations — LangGraph + LangChain agents with behavioral logic, decision frameworks and orchestration on Azure AI Foundry.
  • Built semantic enterprise search with vector embeddings, RAG and Azure AI Search.
  • Implemented agent governance: prompt validation, structured outputs, audit logging, behavior monitoring.
  • Ship distributed microservices on Docker, Kubernetes and Azure Container Apps.
Sep 2024 — Jul 2025
Rhode Island

Cigna

AI Engineer
  • Built healthcare knowledge management, document intelligence and semantic search platforms.
  • RAG with Pinecone, FAISS and Azure AI Search behind Python/FastAPI microservices.
  • Deployment pipelines with Docker, Kubernetes, MLflow, GitHub Actions and Azure ML.
  • AI governance: validation, documentation, auditability, responsible-AI deployment.
Sep 2021 — Dec 2023
India

Deloitte

Data Scientist — Securian Financial · Cardinal Health
  • Production ML on AWS for financial analytics and intelligent automation at Securian Financial.
  • Vector-based semantic retrieval and embedding pipelines — foundational RAG — at Cardinal Health.
  • REST APIs exposing predictive analytics to enterprise platforms; reusable Python ML libraries.
  • Automated ML lifecycle: deployment validation, monitoring, versioning, CI/CD.
Nov 2016 — Sep 2021
India

Accenture

NLP Engineer / Data Scientist — Duke Energy
  • Production NLP for complaint classification, intent detection and text analytics.
  • Predictive maintenance models reducing operational downtime for utility assets.
  • Scalable Python data pipelines and RESTful ML services on AWS.
credentials // 06

Education & recognition.

Education

M.S. — Computers & Information Science
Southern Arkansas University · 2025
B.Tech — Computer Science & Engineering
SRM University, Chennai · 2017

Awards

On the Spot Award
Deloitte · May 2023
Best Team Player Award
Deloitte · Dec 2023
contact // 07

Have a system that
needs governing?

Open to Agentic AI and AI/ML Engineer roles. Email is the fastest way to reach me.

tejaskumar2096@gmail.com +1 945 354 1446 linkedin.com/in/actejas