Priyabart Kumar
LLM Developer
SQL
Rust
Node JS
TypeScript
JavaScript
Java
Python
Active 1 day ago
+91 (8619) 201267 Invite to interview
Message
Download CVCV
Overview
Technical skills
Timeline
Roles
Overview
A Junior-level developer focused on algorithmic problem solving and practice-oriented Java programming. The strongest proven skill is writing correct algorithm and data-structure solutions in Java, evidenced by multiple human-authored files such as DSA/Find First and Last Position of Element in Sorted Array.java and DSA/Merged K Sorted List.java. There is no evidence of production backend work such as API endpoints, migrations, observability, or infrastructure in the human-authored code.
Technical skills
SQL
Rust
Node JS
TypeScript
JavaScript
Java• Junior
Python
Node JS
Prisma
Express
Python
pySpark
Databases
MySQL
Oracle
Pinecone
PostgreSQL
Supabase
Databases
SQLite
ElasticSearch
AI/ML
AI Agents
Claude
ElevenLabs
Gemini
Hallucination
LLM
PyTorch
Qwen
RAG
Scikit-learn
Streamlit
TensorFlow
LangChain
Gradio
huggingface_hub
Transformers
Prompt Engineering
NumPy
Pandas
Spark
Frontend
React Router
React.js
Turborepo
Zod
Three.JS
Vite
React Three Fiber
DevOps
AWS
Docker
Git
Kubernetes
Rest API
Vector
WebRTC
WebSockets
Web3
Anchor
Solana
Cryptography
WebCrypto API
QA
Playwright
Analytics
Tableau
Timeline
Founding Engineer
•
Middle
CollabX
•
Part-Time
Work on a live web application by reproducing reported issues, identifying root causes in the codebase, and shipping fixes with verification. Implement database security controls on the Supabase-hosted backend using row-level security and scoped client access via role-based permissions. Also build and maintain an accompanying Android app for a pre-launch product currently in VC application stage.
Sealed league
AI/ML
Lovely Professional University (LPU)
Bachelor's Degree •
Computer Science & Engineering
Junior Backend Developer
Confidence: Medium Generalist
A Junior-level developer focused on algorithmic problem solving and practice-oriented Java programming. The strongest proven skill is writing correct algorithm and data-structure solutions in Java, evidenced by multiple human-authored files such as DSA/Find First and Last Position of Element in Sorted Array.java and DSA/Merged K Sorted List.java. There is no evidence of production backend work such as API endpoints, migrations, observability, or infrastructure in the human-authored code.
API Design
How well APIs are designed
Not evidenced in public code
Data Layer & Database
Working with databases
Not evidenced in public code
Scalability & Performance
Handling load and speed
Not evidenced in public code
System Architecture
Overall system structure
Not evidenced in public code
Security & Auth
Protecting data and access
Not evidenced in public code
Reliability & Observability
Stability and monitoring
Not evidenced in public code
Verified artifacts
Expertise
Java• Junior
Technologies
Databases
Java• Junior
Recommendations
- Use this developer to implement algorithm-heavy components, coding-challenge libraries, and utility functions where correctness and complexity analysis matter.
- Assign incremental backend tasks that emphasize learning production practices, for example implement small REST endpoints in Java with proper input validation and unit tests under mentorship.
- Have the developer pair on database work that includes schema migrations and simple SQL-driven features to convert algorithmic skill into practical data-layer experience.
Repositories
The developer's experience in this domain has been verified based on AI analysis of the following repositories:
Intern AI/ML Engineer
Confidence: Medium LLM Engineer
LLM-focused engineer at a junior level specializing in agent orchestration and conversational prototypes - strongest at quickly wiring together agent workflows and tools. The strongest proven skill is building simple agent pipelines and task definitions, evidenced by the agent/task composition and LLM instantiation in Tour_planner/Ai_agent.py. The work shows little to no evidence of training pipelines, evaluation infrastructure, MLOps, or production-grade security and testing.
Model Architecture & Training
1/10
How well models are designed and trained
Minimal LLM orchestration and agent composition; no custom architectures, training loops or optimization choices.
Data Pipeline & Feature Engineering
How data is prepared for models
Not evidenced in public code
Experimentation & Evaluation
How results are measured and tested
Not evidenced in public code
MLOps & Deployment
How models are shipped to production
Not evidenced in public code
Computational Efficiency
How efficiently computing resources are used
Not evidenced in public code
Research Depth & Innovation
Depth of research and new ideas
Not evidenced in public code
Expertise
AI Agents & Agentic Workflows• Intern
Conversational AI & Chatbots• Intern
RAG• Intern
Industries
Travel & Tourism• Intern
Technologies
Python
SQL
MySQL
PostgreSQL
Supabase
Rest API
LangChain
Claude
Qwen
Spark
Oracle
Pinecone
WebRTC
WebSockets
ElevenLabs
Scikit-learn
Prompt Engineering
AI Agents
Gradio
huggingface_hub
Transformers
TensorFlow
Pandas
NumPy
Git
SQLite
PyTorch
AWS
Docker
Kubernetes
Gemini
LLM
RAG
pySpark
Streamlit
Vector
Hallucination
Recommendations
- Prototype and extend agentic workflows and tool use - implement more robust tool interfaces, retries, and task decomposition.
- Build small RAG demos that integrate vector stores and retrieval with clear context windows and evaluation metrics.
- Harden prototypes for production - add input/output guardrails, secure model loading, tests, and basic observability for latency and errors.
Repositories
The developer's experience in this domain has been verified based on AI analysis of the following repositories:
Intern Frontend Developer
Confidence: Low Generalist
Frontend generalist at an intern level with exposure to React and WebGL/Three.js stacks. The clearest evidence is the frontend/package.json that lists React, Three.js and @react-three/fiber indicating experimental 3D frontend work. There is little-to-no human-authored application code, state-management logic, tests, or accessibility/performance engineering visible in the vetted files.
UI Component Architecture
How interface parts are built
Not evidenced in public code
Responsive & Cross-browser
Works on all screens and browsers
Not evidenced in public code
Performance Optimization
Speed of the interface
Not evidenced in public code
Accessibility & Semantics
Usable for everyone
Not evidenced in public code
State Management & Data Flow
Managing data in the app
Not evidenced in public code
UX & Visual Polish
Look and feel quality
Not evidenced in public code
Expertise
React• Intern
Frontend Architecture & Build Tools• Intern
Industries
Financial Services• Intern
Technologies
JavaScript
TypeScript
Node JS
Express
Three.JS
Prisma
React.js
Vite
Zod
React Three Fiber
React Router
Turborepo
Recommendations
- Implement small, well-scoped React components that encapsulate 3D view state (position, selection, loading/error), with unit tests and storybook stories.
- Build a focused interactive Three.js demo (one feature) that shows async data loading, loading skeletons, and request cancellation to demonstrate async-state discipline.
- Contribute frontend build-tool and TypeScript configuration improvements (Vite optimizations, typed configs, linting and CI) to raise engineering maturity.
- Prototype a simple Express+TypeScript API endpoint and a React UI that integrates with an LLM backend to show end-to-end frontend-backend interaction.
Repositories
The developer's experience in this domain has been verified based on AI analysis of the following repositories: