Boris Barac
Frontend DeveloperPragueMember since June 21, 2026
AI is analyzing your overall score…
Identifying your key strengths…
Evaluating your skill match against the job requirements…
Assessing your cultural and operational fit
AI is analyzing your overall score…
Identifying your key strengths…
Evaluating your skill match against the job requirements…
Assessing your cultural and operational fit
LLM-Prod-dep-template
June 6, 2026 – Present
template how to deploy a custom LLM to PROD like environment.
View ProjectNapiBench
May 31, 2026 – Present
Performance gains benchmark for usage of NAPI.RS in JS apps
View ProjectmultiBunPass
May 12, 2026 – Present
Multipass is great, but the friction is real. MultiBunPass makes it effortless. Get isolated, Bun-preinstalled Ubuntu VMs in seconds—designed for rapid dev and AI workflows. * AI-Ready: MCP server support for LLM sandboxing. * Instant: Bun installed and folder sync active. * Interfaces: CLI, SDK, and MCP. * Reliable: Smart exec and TCP streaming.
View Projectlinkloom-agent-scraper
April 26, 2026 – Present
Built for **TypeScript and Bun**, this toolkit converts URLs, HTML, and PDFs into clean **Markdown**. It uses **Camoufox** for stealthy JavaScript rendering and handles iframes and tables with ease. Featuring a powerful **CLI** and **MCP Server**, it delivers structured web data directly to AI agents like Claude and Cursor.
View ProjectJekyllMarkdownEditBlog
April 19, 2026 – Present
Template for persona blog. Everything is controlled with markdown files
View ProjectpopUpControlChromeExtension
February 2, 2026 – Present
Simple extension to control popUp windows globally. This windows are used by banks and stock platforms, so it can be useful.
View Projectmicroservice-mcp-youtube
November 6, 2025 – November 6, 2025
Project for upcoming YouTube series
View ProjectLora-Fine-Tuning-Pipeline
October 30, 2025 – Present
Fine-tune language models on Apple Silicon (MPS) and NVIDIA GPUs (CUDA) with Metaflow orchestration, Unsloth/PyTorch training, and Polars data processing. The pipeline converts documents to text, generates synthetic QA pairs with a teacher model, and fine-tunes a student model via LoRA.
View ProjectCultural Fit Analysis
The candidate's personal projects demonstrate a strong inclination towards self-directed learning and exploration of diverse technologies, including AI/ML and infrastructure. While this shows initiative, the majority of projects are not directly aligned with typical enterprise-level frontend development, which might indicate a different focus or require adaptation to standard team workflows and established frontend frameworks. The breadth of technologies suggests a curious mindset, but also a potential lack of deep specialization in core frontend frameworks (e.g., React, Angular, Vue).
Soft Skills & Operational Fit
Insufficient data to assess soft skills or operational fit. The candidate's project descriptions are concise, but there is no information on collaboration, problem-solving approaches, or communication style in a team setting.