I design and implement systems at the boundary between classical software engineering and applied AI — specifically:

• Autonomous agent loops that plan, execute, and self-correct over multi-step coding tasks
• Retrieval pipelines that ingest messy real-world documents and serve precise, ranked context to LLMs
• CLI/TUI tooling that runs locally, requires no cloud dependency, and treats safety as a design constraint

My engineering approach is shaped by one conviction: language models are only as useful as the infrastructure surrounding them. I focus on that infrastructure.

A terminal-native agent that operates on a full repository — not just individual files. Operon builds a persistent, hash-gated symbol graph across the entire codebase, then uses it to execute multi-file refactors, generate structured documentation, and answer questions about execution flow.

Key engineering decisions:

• Deterministic-first REVIEWER: verifies changes by comparing disk hash to diff memory snapshot before any LLM call — eliminates hallucinated confirmation
• CRUD fast-path: structured operations (import insertion, variable renaming, comment placement) handled via tokenize and ast without LLM — removes the most common failure mode of small local models
• 5-tier surgical diff engine: SEARCH/REPLACE patching with cascading fallbacks from exact string match through fuzzy multi-line tolerance
• Mandatory approval gate: no filesystem write occurs without explicit human confirmation; timeout auto-rejects to prevent hang
• 9-provider LLM router with hot-reload config — model switching takes effect on the next call, no restart

→ github.com/qasimio/Operon

A retrieval system designed for the documents that most RAG demos ignore: scanned PDFs, PPTX speaker notes, multi-sheet Excel files. The engineering focus is retrieval correctness under real document conditions.

Key engineering decisions:

• Custom OCR pipeline (Tesseract + Poppler) handles flattened text and image-only pages
• Hybrid search: dense vector retrieval re-ranked by a Cross-Encoder, yielding ~40% precision improvement over cosine similarity alone
• Session-isolated storage handler resolves Windows file-locking failures (WinError 32) in persistent vector stores
• Context injection optimized to reduce token usage by ~60% without precision loss

→ github.com/qasimio/MQNotebook · Live Demo

A search engine for Computer Science literature built without Lucene or ElasticSearch. The goal was to understand retrieval at the data-structure level before building RAG systems on top of it.

Key engineering decisions:

• Positional inverted index with O(1) keyword lookup via custom hashing
• Offline Indexer pre-processes corpora at build time, pushing query latency to sub-millisecond
• O(L) Trie for prefix-completion; Levenshtein distance for fuzzy matching
• TF-IDF scoring with behavioral re-ranking

The classical IR knowledge from DevShelf directly informs the hybrid search design in MQNotebook.

→ github.com/qasimio/DevShelf

A published CLI tool that keeps directories clean automatically — organizing 240+ file extensions across 30+ categories with background watch mode, full undo, deduplication, and custom category configuration. Designed for data pipeline preparation, ML dataset cleaning, and anyone who wants their Downloads folder to organize itself.

pip install foldr                          # one install, everything included

foldr ~/Downloads --preview               # see the full plan before anything moves
foldr ~/Downloads                         # organize (preview → confirm → move)
foldr ~/Downloads --recursive --depth 2   # include subdirectories
foldr watch ~/Downloads                   # organize now + keep watching forever
foldr undo                                # restore the last operation instantly

Key engineering decisions:

• Background daemon architecture: foldr watch spawns a detached OS-native subprocess that runs indefinitely — using inotify (Linux), kqueue (macOS), or ReadDirectoryChangesW (Windows) — 0% CPU when idle; terminal returns immediately
• Two-phase watch pipeline: initial full-directory scan on daemon start organizes existing files, then event-driven processing handles every subsequent arrival — files moved back to root are re-organized; no one-time-only moves
• JSON undo system: every organize operation writes an immutable history entry; foldr undo reverses any operation independently — git-revert semantics applied to filesystem state
• 240+ extensions, 30+ categories: Documents, Images, Videos, Audio, Code, Archives, Executables, Databases, Machine Learning models, and more — all configurable via TOML
• Zero external dependency for output: ANSI rendering via ctypes (Win10+) with colorama fallback — no rich, no pyfiglet, no curses
• Conflict-safe moves: resolves filename collisions by appending _(1), _(2) — never overwrites existing files

foldr ~/Downloads --dedup keep-newest     # remove duplicate files (preview first — irreversible)
foldr history                             # browse all past operations with IDs
foldr config --edit                       # open category config in your editor
foldr watch ~/Downloads --recursive       # watch and organize subdirectories too

→ github.com/qasimio/foldr · pypi.org/project/foldr

• Extending Operon's symbol graph to JS/TS via Babel AST integration
• LSP server mode for editor integration
• Structured output evaluation framework for RAG retrieval quality