Miraziz Mukhammedov
AI Engineer
SQL
TypeScript
Node JS
Python
Active 6 days ago
+998 (97) 8922009 Invite to interview
Message
Download CVCV
Overview
Technical skills
Roles
Overview
Frontend developer (Middle) specialized in TypeScript React/Next.js integrations with AI-backed services and real-time document processing. The strongest proven skill is building API client and realtime status flows as shown by src/lib/api/client.ts (ApiError and apiRequest) and src/lib/ws/document-status.ts (connectDocumentStatusSocket). There is little public evidence of custom component libraries, systematic a11y automation or measured performance work.
Technical skills
SQL
TypeScript• Junior
Node JS• Junior
Python
Python
SQLAlchemy
Alembic
Asyncio
Pydantic
Uvicorn
FastAPI
Databases
PostgreSQL
Qdrant
Redis
AI/ML
Embeddings
LLM
Prompt Engineering
RAG
Semantic Search
OpenAI SDK
Frontend
React.js
Next.js
Tailwind CSS
DevOps
Docker
Docker Compose
Git
Rest API
WebSockets
Mobile
Clean Architecture
QA
Swagger
Junior Frontend Developer
Confidence: Medium App Engineer
Frontend developer (Middle) specialized in TypeScript React/Next.js integrations with AI-backed services and real-time document processing. The strongest proven skill is building API client and realtime status flows as shown by src/lib/api/client.ts (ApiError and apiRequest) and src/lib/ws/document-status.ts (connectDocumentStatusSocket). There is little public evidence of custom component libraries, systematic a11y automation or measured performance work.
UI Component Architecture
2/10
How interface parts are built
API- and hook-first structure is present (useDocuments, api client) but there is little evidence of deliberate UI component architecture, design-system work, or custom component lifecycle patterns.
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
3/10
Managing data in the app
Clear server-state handling and real-time status handling via an API client and a WebSocket helper; shows pragmatic error wrapping and token management but lacks advanced patterns such as optimistic updates with rollback or extensive request-cancellation logic.
Evidence
Miraziz77/studygraph-frontend/src/lib/api/client.ts: ApiError, getToken/setToken/clearToken and apiRequest wrapper
Miraziz77/studygraph-frontend/src/lib/ws/document-status.ts: connectDocumentStatusSocket WebSocket helper
Miraziz77/studygraph-frontend/src/hooks/useDocuments.ts: upload and remove functions for document lifecycle
UX & Visual Polish
2/10
Look and feel quality
Basic UX edge-state handling (loading/error) visible in hooks and API calls, but no consistent skeletons, undo patterns or measured perceived-performance artifacts.
Expertise
React• Junior
Modern Web Frameworks• Junior
Industries
Education• Junior
Technologies
TypeScript• Junior
Node JS• Junior
Tailwind CSS
Next.js
WebSockets
React.js
Frontend• mentioned only
Recommendations
- Build and iterate chat and RAG frontends that integrate with AI backends, including chat session flows and document upload UX.
- Implement real-time document-processing UX and WebSocket-backed status pages, improving edge states and retries.
- Develop API client libraries, auth/token handling, and typed TypeScript wrappers for backend endpoints and error surface.
- Work on Next.js TypeScript features and server-client boundaries for AI-assisted features (SSR/RSC & client hooks).
Repositories
The developer's experience in this domain has been verified based on AI analysis of the following repositories:
Intern AI/ML Engineer
Confidence: Low Generalist
Backend developer at a junior level focused on building AI-backed REST services and integration work. The strongest proven skill is assembling LLM-backed service integrations using FastAPI and OpenAI-based calls with vector search and caching components as shown by service and API modules that integrate OpenAI, Redis and a vector store. There is little or no evidence of custom model training, MLOps pipelines, performance engineering, or test coverage in the publicly analyzable human-authored files.
Model Architecture & Training
How well models are designed and trained
Not evidenced in public code
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
LLM• Intern
Industries
Artificial Intelligence• Intern
Technologies
Python
SQL
PostgreSQL
Redis
Rest API
Docker Compose
Qdrant
FastAPI
Embeddings
Prompt Engineering
OpenAI SDK
Git
Docker
LLM
RAG
Asyncio
Semantic Search
RAG• mentioned only
Recommendations
- Build LLM-powered RAG APIs and chat endpoints using FastAPI and OpenAI integration where the developer handles request/response, caching and vector search.
- Implement end-to-end document ingestion and vector indexing pipelines with robust error handling and background processing for production readiness.
- Add reproducible evaluation and experiment tracking when tuning prompts or retrieval configurations, and add unit and integration tests for API and service code.
Repositories
The developer's experience in this domain has been verified based on AI analysis of the following repositories:
Intern Backend Developer
Confidence: Low API Engineer
Backend developer early in their career focused on Python and FastAPI for AI-powered document ingestion and conversational features. The strongest proven skill is assembling end-to-end AI-backed document workflows including JWT-based auth, document upload and indexing, embedding generation and WebSocket status flows as evidenced by the stack choices and feature surface. There is limited evidence of mature production practices such as iterative migration history, structured observability, comprehensive test coverage and resilient operational controls like retries with backoff or circuit breakers.
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
Expertise
Python• Intern
Backend AI & LLM• Intern
Databases & Vector Storage• Intern
Messaging & Real-time• Intern
Node.js• Intern
Industries
Education• Junior
Artificial Intelligence• Intern
Technologies
SQLAlchemy
Pydantic
Uvicorn
Alembic
Recommendations
- Develop small, focused backend features end-to-end (REST endpoints + DB migrations + tests) to demonstrate ownership and production-readiness.
- Add integration and unit tests plus CI pipelines to prove quality and enable higher-tier evaluation.
- Implement and document resilience patterns (timeouts, retries with exponential backoff and jitter, graceful shutdown) around external calls such as OpenAI, vector DB and Redis.
- Build iterative schema migrations showing evolution (not only initial create) and include explicit transaction boundaries for non-trivial DB operations.
Repositories
The developer's experience in this domain has been verified based on AI analysis of the following repositories: