Looks like you have JavaScript disabled. For the full Twine experience, you will need to re-enable it.

Full-stack engineer focused on Applied AI and LLM integration, building production-ready systems across backend and frontend. I ship multi-tenant SaaS platforms, causal/AI simulation pipelines, and GPU-accelerated media services—turning complex requirements into reliable software through testing, code review, and careful architecture.…

Brilliant Makanju

Full Stack Developer, AI Engineer, Web Developer, +5





Full-stack engineer focused on Applied AI and LLM integration, building production-ready systems across backend and frontend. I ship multi-tenant SaaS platforms, causal/AI simulation pipelines, and GPU-accelerated media services—turning complex requirements into reliable software through testing, code review, and careful architecture.…

Available to hire

Full-stack engineer focused on Applied AI and LLM integration, building production-ready systems across backend and frontend.
I ship multi-tenant SaaS platforms, causal/AI simulation pipelines, and GPU-accelerated media services—turning complex requirements into reliable software through testing, code review, and careful architecture.

Skills

Experience Level

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Intermediate

Intermediate

Language

Work Experience

Real-Time YouTube Communication Tool (RepoThreadChat)

June 1, 2026 - July 1, 2026

Solo-built a Rust (Axum) backend and SvelteKit frontend using WebSockets for real-time messaging, reactions, and threaded replies, without external state libraries. Learned Rust and SvelteKit from scratch and shipped a functional MVP in under two months.

GPU Video Microservice (PlaythroughProcessor)

December 1, 2025 - January 1, 2026

Developed a GPU video microservice in Python using FFmpeg, tuned for NVIDIA RTX-class and RunPod environments. Utilizes hardware NVENC/NVDEC encode/decode, CUDA-accelerated scaling, and VRAM-fraction management across quality presets. Processes input video plus a JSON edit-map timeline for parallel segment cutting, GPU concatenation, watermark overlays, and color grading.

Causal Simulation Engine (BranchForge)

December 1, 2025 - January 1, 2026

Built a 7-stage pipeline (Django, Python, LLaMA 3.3) that constructs directed acyclic graphs from grounded facts, enforces acyclicity via topological sort, and propagates counterfactual interventions along causal edges. Implements SHA-256 branch hashing for Git-like scenario versioning and outputs schema-validated JSON with calibrated confidence scores. Uses a minimum-confidence threshold to gate execution/halts when confidence is too low.

Independently Architected & Shipped Multi-Tenant SaaS Platform (Push to Draft)

January 1, 2025 - January 1, 2026

Architected a multi-tenant Django backend using schema-isolated PostgreSQL per tenant (django-tenants) with JWT auth and multi-provider billing (Paddle, Dodo Payments). BranchForge runs as a module within the same backend, sharing tenant, auth, and billing layers. Core product converts GitHub commits into scheduled, platform-tailored social posts via AI prompt generation and OAuth-connected integrations, with credentials encrypted at rest (AES-256).

Frontend Developer → AI Engineer at Confidential Startup (NDA)

December 1, 2023 - October 1, 2025

First frontend hire on a 4-person engineering team; later became the company’s primary AI engineer. Built responsive UIs in React/Next.js, maintained a 90+ Core Web Vitals average, and standardized the codebase with 15+ reusable components and 5+ integrated REST APIs. Transitioned into AI engineering by shipping RAG features on AWS Bedrock via a Python/FastAPI service layer on AWS Lambda. Configured AWS S3 for file/data storage and set IAM permissions for Lambda. Contributed to overall technical architecture and stack decisions alongside the engineering team.