1 · AI
2 · Web / Full-stack
3 · Architecture & systems
4 · Science & research
LLM
ML
Backend
Databases
Frontend
Infrastructure & DevOps
Product design
AI / LLM systems: LLM features built around queues, data contracts, workflows and operation.
AI / LLM
systems
Agent workflows: Multi-step processes, scenario graphs and tools with explicit data flow.
Agent workflows
Prompt engineering: System instructions, reusable prompts and versioned configurations.
Prompt
engineering
Structured output: Response schemas, parsing and typed contracts between models and applications.
Structured
output
Local LLMs: Private inference with open-weight models, llama.cpp and a dedicated gateway.
Local LLMs
Applied ML: Applied neural networks, clustering and recommendation logic.
Applied ML
Neural networks: From early neural network projects to modern LLM applications.
Neural networks
PyTorch: Training and comparing PyTorch models: a typing-rhythm VAE and flow models for motion trajectories.
PyTorch
Generative models: Generating new temporal sequences with VAE and normalizing flows; comparing distributions rather than training loss alone.
Generative
models
Clustering: Grouping episodes by motion characteristics and context to inspect the composition of a research corpus.
Clustering
ML data preparation: Cleaning public logs, retaining provenance and distribution tails, and splitting data by participant and session.
ML data
preparation
Model evaluation: Comparing ML model quality through controlled experiments, reproducibility and careful interpretation of results.
Model
evaluation
Recommendation systems: E-commerce recommendation logic and product research.
Recommendation
systems
Backend engineering: APIs, background jobs, integrations and service data.
Backend
engineering
Python: AI services, FastAPI, research prototypes and infrastructure tools.
Python
FastAPI: Typed Python APIs for product and research applications.
FastAPI
PHP / Laravel: Full-stack and backend development across marketplaces, CRM and platforms.
PHP / Laravel
Queues & workers: Background execution, retries, load distribution and task hierarchies.
Queues &
workers
Kafka: Messaging integration for a medical microservices platform.
Kafka
PostgreSQL: Relational data models for backend services.
PostgreSQL
MySQL: Schemas, queries, CRM, marketplaces and data migration.
MySQL
SQLite: Embedded relational storage for local applications.
SQLite
MongoDB: Document storage and application data modeling.
MongoDB
JS / TS: From jQuery and AngularJS to typed Vue and Nuxt applications.
JS / TS
Vue / Nuxt: Product interfaces, dashboards and server-rendered applications.
Vue / Nuxt
SSR / SEO: Server rendering, search-friendly structure and long-lived product content.
SSR / SEO
Interactive maps: Visual interfaces for zones, routes and geographic constraints.
Interactive
maps
Linux / SSH: Server maintenance, health checks and installation workflows.
Linux / SSH
Nginx / load balancing: Gateway routing and distribution of inference requests.
Nginx / load
balancing
Orchestration: Repeatable installation, deployment and maintenance workflows across servers.
Orchestration
Docker: Isolated recording bots, agents and repeatable service deployment.
Docker
CI/CD & Git automation: GitHub/GitLab hooks and controlled application updates.
CI/CD & Git
automation
Observability: Dashboards, telemetry, health checks and task monitoring.
Observability
Security operations: Collection of system events and operational logs for investigation.
Security
operations
Product UI / UX: Complex forms, graph editors, dashboards and focused user journeys.
Product UI / UX
Product development: Discovery, UX, implementation, feedback and long-term product evolution.
Product
development
Product architecture: Connecting domain models, user journeys and runtime constraints.
Product
architecture
Domain modeling: Entities, rules and states for complex product domains.
Domain modeling
Graph structures: Graph models for conversations, AI scenarios and task execution.
Graph
structures
Microservices: Legacy decomposition, service communication and explicit data contracts.
Microservices
Event-driven architecture: Event-based integrations, message brokers and background processing.
Event-driven
architecture
Geospatial services: Backend services for geographic classification, spatial rules and geodata: from flight approvals to emergency call maps and ambulance movement.
Geospatial
services
Applied research: Learning new domains and translating knowledge into working models.
Applied
research
Protein structures: Research prototypes using structural protein data.
Protein
structures
Aromatic molecules: Research data, chemical profiles and sources for an aroma product.
Aromatic
molecules
Geographic regulations: Translating regional rules and approval processes into product workflows.
Geographic
regulations