Mohammed Affan
Software Developer
Profile
Software developer at Pollinations.ai and Myceli.ai focused on AI infrastructure, agents, and developer tooling. Builds MCP integrations, streamed APIs, incremental retrieval, and workflow automation, with additional work in Rust systems, web, mobile, and interactive 3D.
Experience
Pollinations.ai
Feb 2025 – PresentDeveloper · MLOps & AI Infrastructure
- Build AI agents, model integrations, APIs, and workflow automation for the Pollinations platform.
- Extended the MCP server with tools for image batches, video generation, multimodal analysis, transcription, search, and pricing; added dynamic model discovery and API-key authentication.
- Contribute to Polli across Discord, GitHub, and OpenAI-compatible APIs, connecting repository search, session context, caller-scoped tools, model routing, and streamed responses.
- Moved repository embeddings into Cloudflare Vectorize with incremental indexing, batched embedding requests, and removal of vectors for deleted files.
- Replaced per-user database update subprocesses with batched operations and concurrent API validation; isolated Cloudflare shell execution in disposable containers without caller credentials.
Myceli.ai
Feb 2025 – PresentDeveloper · AI Systems & Automation
- Connect AI infrastructure through automations and workflows, connecting models, services, and agent modules across cloud and local environments.
Selected projects
Memory-Arc
Public source · PythonBuilt a configurable agent-memory engine separating recent history, processing policy, persistent vector retrieval, and model-provider adapters.
Agent evaluation environments
Public source · OpenEnv hackathonBuilt Compliance Auditor and WarRoom with procedural investigations, MCP tools, evolving state, and adversarial tests for reward shortcuts.
Ouroboros
ML research · In developmentBuild language-model research prototypes in PyTorch, compare experiments against explicit baselines, and document limitations in research notes. Unpublished methods remain private.
Sylph
Local AI systems · In developmentDevelop a Rust-based local AI runtime exploring inference, task-driven learning, and peer-to-peer adapter exchange, with compatibility checks, payload validation, and composition testing.
Repository intelligence
Private · Rust developer toolingDevelop local repository-analysis tooling in Rust with SQLite/FTS5, Tree-sitter, structured evidence retrieval, and validation context for developers and coding agents.
Application engineering
Private · Web, mobile & 3DBuilt a Flutter records app with Supabase and reporting; developed a Next.js presentation builder with streamed generation; built SceneForge for interactive, streamed 3D scenes.
Technical skills
Languages: Python, TypeScript / JavaScript, Rust, Dart, SQL.
AI & MLOps: PyTorch, model fine-tuning, local inference, model deployment, MCP, agent orchestration, RAG.
Infrastructure: Cloudflare Workers, Vectorize, D1, Docker, Kubernetes, Helm, Linux, GitHub Actions.
Applications & data: FastAPI, React, Next.js, Flutter, Three.js, Qdrant, SQLite, Supabase.
Education
Diploma — AI/ML pathway
MS Ramaiah Polytechnic