[ SYSTEM INITIALIZATION ]
> LOADING MODULES... OK
> ESTABLISHING CONNECTION... OK
>

Swayam R. Gavankar

> Systems, Backend & AI Optimization Engineer | Specializing in Rust, Go, LLM SFT & Low-Level Systems
[ SCROLL DOWN TO CONTINUE ]

[ NARRATIVE_PROFILE ]

I am Swayam R. Gavankar, a systems and backend engineer specializing in low-level optimization, microservices architecture, and agentic workflows. With a background in multi-year backend development, I excel at moving systems from zero to production while eliminating architectural overhead. I take a highly disciplined approach to development, featuring a structured method of agentic coding where I write strict design blueprints and plans for AI agents to execute. This workflow maximizes efficiency, minimizes hallucinations, and guarantees clean, deterministic codebases. As a quick and adaptive learner, I rapidly master new technologies through documentation. Currently, I have completed my 12th-grade education and am preparing for undergraduate engineering admissions, continuing to build high-performance systems and local AI tooling.

[ SKILLS & CAPABILITIES ]

> SYSTEMS, BACKEND & OPS
[ Go (Preferred / Highly Rated) ][ Rust (Preferred / Highly Rated) ][ C++ (Low-level systems) ][ Python (FastAPI, Django, scripts) ][ JavaScript / TypeScript (MERN stack, UI) ][ Microservices & System Design ][ PostgreSQL, SQLite, Redis ][ Docker & Containerization ][ Debian Server Administration ][ Git & GitHub Operations ]
> AI, ML & SYSTEM OPTIMIZATION
[ Agentic Workflows & Multi-Agent Routing ][ Supervised Fine-Tuning (SFT) & PEFT ][ LoRA, QLoRA, TRL, Transformers ][ Local SLM Deployments (llama.cpp, LiteRT) ][ Structured Output Tuning (JSON / YAML) ][ High-Performance Code Optimization ][ Manual Debugging & Systems Tools ][ Data Analysis (Pandas & NumPy) ][ Intermediate Frontend Development ]
> EXECUTION STYLE
  • Strict Documented Agentic Planning: Writing strict plan documents and blueprints for AI agents to follow, optimizing API costs and preventing bugs.
  • Low-Level Manual Debugging: Resolving obscure runtime issues and software anomalies through hands-on tracing with low-level debuggers and system diagnostic tools.
  • Technical Adaptability: Self-directed learner capable of rapidly self-starting and picking up new technologies given good technical documentation.
  • Rapid Prototyping: Rapid software prototyping within compressed timelines, proven through hackathons and independent delivery.

[ PAST_PROJECTS ]

>Stric: High-Performance QUIC & Flow Mesh Networking(Open Source)

Authored a high-performance network transport and mesh routing ecosystem in Rust built on QUIC. Includes `stric-core` (symmetric P2P wrapper over `quinn`), `stric-tower` (an `axum`-like request-response framework), and `stric-flow` (topic-based mesh routing and state sync engine using Dijkstra calculations).

#Rust#QUIC#Asynchronous#P2P Mesh#Tower#Dijkstra
>env-doctor: Runtime Compatibility & ML VRAM Estimator(Open Source (Hackathon))

Designed and engineered in a compressed 2-day hackathon timeline. Built as a local-first CLI utility and compatibility inspector for the HuggingFace + PyTorch + CUDA ecosystem. Features precise VRAM/OOM estimation for LLMs (accounting for KV cache size, sequence length, and quantization) and an automated AI-powered incompatibility reporter using Watsonx Orchestrate.

#Python#PyTorch#CUDA#HuggingFace#Watsonx#MCP
>Mandala Workspace: Distributed Hierarchical Filesystem(Open Source)

Engineered a secure, distributed, automatically-versioned hierarchical monorepo workspace. Implemented challenge-response authentication (Ed25519), PASETO session management, local keyring encryption (AES-256-GCM, Argon2id), custom folder access control bitmasks, and hierarchical cache invalidation via Redis.

#Go#gRPC#Wails v2#React#PostgreSQL#Redis#Cryptography
>Student Buddy: Privacy-First AI Academic Advisor(Open Source)

Created a local-first, privacy-focused desktop assistant using local SLMs. Built a multi-agent orchestrator utilizing specialized prompts and model adapters (Policy, Academic, Mental Health, Fusion agents), local client state encryption (AES-128-CBC + HMAC-SHA256), and Next.js + MUI frontend.

#FastAPI#Next.js#llama.cpp#Gradio#Multi-Agent#AES Encryption
>Proprietary Options Trading Microservice(FinTech Client (Proprietary))[ CONFIDENTIAL ]

Engineered a small but efficient proprietary options trading microservice in Python using Pandas, NumPy, and FastAPI to process trading orders and option chains in milliseconds. System processes millions of trading symbols and 1000s of options concurrently, executes custom business logic, manages real-time active trade states, and handles automatic exit signals via trading APIs.

#Python#FastAPI#Pandas#NumPy#Concurrency#Trading APIs
>Blogistan: Full-Featured Blogging & Interaction Engine(Open Source)

Built a server-side rendered blogging platform using Django and Django Rest Framework. Programmed an asynchronous, client-side commenting and reply system leveraging browser fetch APIs and CSRF validation, integrated with locally-bundled Summernote WYSIWYG editor.

#Django#Python#SQLite#REST API#JavaScript#Summernote