AI fullstack systems engineer

JAYAKRISHNAASubramaniyanRavichandran

Chennai, India

Engineering intelligence

AI that thinks
in systems.

I design production AI that can reason, remember, recover and earn trust—from clinical copilots to self-healing infrastructure.

Live architectureActive
LangGraph · RAG · MLOps

Selected systems · 2023—2026

Built for consequence,
not for the demo.

Each system is designed around the harder questions: evidence, memory, failure, cost and human control.

01Clinical intelligence

VetAssist AI

AI/ML Engineer · Sanchu Animal Hospital

A guarded clinical copilot that moves veterinarians through diagnosis in the right order—then validates every recommendation against protocols, literature and model reasoning.

No raw model output reaches the clinician.

  • LangGraph
  • GPT-4o Vision
  • Redis
  • MongoDB
  • PubMed
02Multimodal pet triage

Pawspector AI

AI/ML Engineer · Sanchu Animal Hospital

A multi-graph triage assistant that understands free-form concerns, photographs and mixed inputs—then routes each conversation to the right specialist workflow.

Zero hardcoded keyword routing.

  • LangGraph
  • GPT-4o Vision
  • L1 Cache
  • Redis
  • MongoDB
03Grounded enterprise RAG

Website Internal Knowledge Chatbots

AI/ML Engineer

An internal assistant that searches company knowledge before it speaks, grounding each response in the organisation’s own material instead of generic model memory.

Company truth before model confidence.

  • RAG
  • OpenSearch
  • Vector Search
  • OpenAI API
  • FastAPI
04Autonomous operations

Self-Healing CI/CD

Designer & Builder

An eight-agent remediation system that watches delivery pipelines and Kubernetes, gathers evidence, identifies causes and safely resolves low-risk failures.

The model proposes. Deterministic policy decides.

  • Multi-agent AI
  • LangGraph
  • Kubernetes
  • GitHub Actions
  • MLOps

Point of view

I build the intelligence
and the system around it.

Models are only one layer. Useful AI also needs orchestration, evidence, memory, evaluation, observability and a safe way to fail.

01

Ground before generating. Retrieval and protocol evidence come before confident output.

02

State is a product decision. Memory is designed for continuity, cost and safe rollback.

03

Autonomy needs boundaries. Models can propose; deterministic policy controls the blast radius.

Working vocabulary

Capabilities

01

Agentic & GenAI

LangGraph · RAG · LLM evaluation · Prompt systems · Conversational AI

02

Machine learning

NLP · Computer vision · Classification · Forecasting · Recommendations

03

Platforms

Python · FastAPI · SQL · PySpark · Redis · MongoDB · OpenSearch

04

Cloud & delivery

AWS Bedrock · SageMaker · Lambda · Docker · Kubernetes · CI/CD · MLflow

Experience

From analysis
to autonomous AI.

Chennai, India

  1. 01

    2025 — 2026

    AI/ML Engineer

    Cavin Infotech

    Designed and shipped three production LangGraph systems across veterinary triage, clinical decision support and enterprise knowledge retrieval.

  2. 02

    2023 — 2025

    Data Scientist

    KMU Techgrid Solutions

    Owned machine-learning lifecycles across finance, computer vision and conversational AI, with production deployments on AWS.

  3. 03

    2022 — 2023

    Data Analyst

    KMU Techgrid Solutions

    Turned operational data into decision-ready reporting and supported early ML and GenAI prototypes for business teams.

Earlier explorations

Computer vision,
prediction & edge AI.

01

Maize Disease Detection

Deep learning · Image classification

02

Wine Quality Analysis

Predictive modelling

03

Iris Recognition

Computer vision · Biometrics

04

Fingerprint Recognition

Feature extraction · Authentication

05

Road Sign Recognition

Edge AI · Raspberry Pi

Education

B.E. Electronics & Communication Engineering

PRIST University · 2013—2017

Available for the right problem

Let's build AI
that holds up.

srkrishnaa0@gmail.com
Jayakrishnaa Subramaniyan RavichandranAI Engineer · Data ScientistChennai, India