MODEL LAYER
Foundation reasoning & multimodal intelligence powering structured workflows.
GPT-4oClaude 3GeminiLlamaHuggingFace
Used in multi-agent orchestration, structured RAG, and enterprise automation.
1.5+
Years of hands-on experience
Tech Stack
Agent Orchestration
LangGraphCustom Agent WorkflowsOpenRouter APIStructured Prompt Engineering
Vector DBs & RAG
FAISSChromaDBRAG Pipelines
Backend & Auth
PostgreSQLMulti-Tenant SaaSJWTOAuth2
"Intelligence is powerful — but engineered intelligence changes the world."
— Likhith Kumar Masura
Intelligence Architecture
API & INTEGRATION LAYER
Provider abstraction and multi-model switching via unified interfaces.
OpenAI APIAnthropic APIGemini API
Client → API Gateway → Model Provider
DATA & RETRIEVAL LAYER
Contextual grounding using vector search and structured retrieval pipelines.
FAISSChromaDBRAG PipelinesData ExtractionResilient Ingestion
User Query→Embed→Vector Search→Context Injection→Model
AGENT ORCHESTRATION
Stateful, multi-step reasoning systems with graph-based execution.
LangGraphCustom Agent WorkflowsOpenRouter APIStructured Prompt Engineering
Planner→Tools→Memory→Executor→Output
BACKEND & SECURITY
Authenticated, access-controlled, production-grade APIs.
PostgreSQLMulti-Tenant SaaSJWTOAuth2RBAC
RBACRate LimitingSecure Token Handling
PERCEPTION & DEEP LEARNING
Vision pipelines and domain-specific model training.
Deep LearningPyMuPDF (PDF reading / thumbnails)Pillow (image processing)pypdf
CNNMultimodal ProcessingEdge Inference
DEPLOYMENT & MONITORING
Scalable deployment with logging, monitoring and CI/CD.
LoggingCI/CDAPI Monitoring
Latency · Error Rate · Throughput · Cost
CLOUD INFRASTRUCTURE
Elastic compute across cloud and serverless environments.
AWSAzureGCPCI/CD
Selected Projects
1 / 7
AgenticAI Data Labeling Platform
Problem
Data labeling is the bottleneck of modern AI.
Solution
The system uses a Hub-and-Spoke agent architecture.
Impact
Reduced TTM (Time to Market) by 4 months; Surpassed human-crowdsourced accuracy
Click to view details and links
More projects
A Deep Learning Model for auto capturing image by detecting smile
Python
Developed a model that automatically captures an image when a person or group smiles. Used OpenCV DNN Face Detector, Haarcascade Algorithm and a deep learning framework for real-time detection.
Tech
PythonOpenCVDeep LearningAI
Deep Dive Case Studies
Narratives of engineering journeys, from architectural decisions to deployment challenges.
Recent Blogs
View AllNo blog posts yet.