Interface
Composable UIs, design systems, and micro-frontend surfaces
Composable UIs, design systems, and micro-frontend surfaces
APIs, event-driven workflows, and distributed backends
Schema design, caching layers, and data integrity at scale
Serverless, observability, and global delivery infrastructure
8+ years shipping full-stack products and AI systems that multiply team output. Sole architect of HustleSasa platform ($50K→$900K+/mo payments). I design GTM automations, agent workflows, and internal tools that give departments 5–10× leverage — engineered systems with eval gates and production reliability, not chatbots bolted on the side.
From AI agent pipelines and GTM automations to Vue, React, and Svelte frontends, serverless backends, and edge deployments. I build systems that scale across every layer — commercial and technical.
Agent workflows, enrichment pipelines, and cross-department automations that wire CRMs, outbound tools, and LLMs into one revenue engine with guardrails and measurable outcomes.
Decompose monoliths into independently deployable services with clear domain boundaries, resilient communication, and observable pipelines.
Event-driven, pay-per-use architectures on AWS and edge runtimes, from API gateways to background workers with zero idle cost.
Module federation and independent frontend teams shipping Vue, React, and Svelte apps that compose into a unified product surface.
Global delivery via Cloudflare Workers, CDN caching, and cloud-native infra with low latency from browser to database.
Full-stack hospital management system for clinics in Ghana: patient registration, OPD triage, billing, and role-based access
High-performance automotive data autofill engine rewritten in Rust
Consulting GTM system: Clay enrichment and signal triggers feed n8n orchestration and HubSpot CRM, with LLM agents handling lead research, personalized outbound, and inbound routing — eval gates before anything reaches a prospect.
Serverless platform for automating approval and workflow routing across departments
Visit ↗GraphQL library for building schema-first APIs with minimal boilerplate
Repository ↗GitHub Action for deploying SST applications to AWS with zero config
Repository ↗TypeScript is home base, but I reach into other languages when the problem demands a different shape: memory safety, numeric performance, or AI-native tooling.
Home base for full-stack delivery: typed Vue/React frontends, Node services, shared contracts, and the layer where most production systems are designed and shipped.
Hands-on experimentation with systems programming: memory safety, concurrency, and performance patterns before committing them to production paths.
Heavy use when the problem calls for it: AI agent pipelines, GTM automations, data scripting, and fast backend prototyping — the default reach for LLM-powered systems.
Early exploration for machine learning workloads: Python-like ergonomics with a path toward bare-metal performance for model-centric systems.
GTM engineering is where commercial instinct meets code. I build the automated systems behind outbound, inbound routing, CRM enrichment, approval workflows, and cross-department ops — wired with LLMs and APIs so marketing, sales, and operations run faster without hiring linearly.
Marketing, sales, CS, finance, HR — any team with repetitive workflows gets custom tooling. I map the bottleneck and ship the system, not a one-size template.
Lead research, personalization, enrichment cascades, and signal-triggered outbound — encoded as agent workflows with eval gates, not one-off prompts.
CRM, enrichment, outbound, analytics, internal APIs — composed into one pipeline. Data flows in, qualified action flows out.
Replace weeks of manual work with autonomous workflows. Outcomes: hours saved, pipeline velocity, conversion lift — engineered, measured, iterated.
I do not sprinkle GPT calls on features. I engineer AI systems: agent orchestration, evaluation frameworks, inference pipelines, and the reliability layer that turns demos into production. Current work includes LLM eval and QA at Invisible Technologies — the same rigor I bring to client automations.
Multi-step LLM workflows for research, enrichment, routing, and follow-up — with tool use, guardrails, and human handoff when confidence is low.
Designing rigorous eval frameworks for LLM outputs: quality scoring, regression detection, and production safety gates before anything ships.
Latency, context windows, batching, and deployment patterns for making models fast, observable, and dependable in real products.
Transformers, attention, embeddings, and how architecture choices shape capability and cost — so production systems are designed with limits in mind.
Engineering is the craft, but balance keeps the edge sharp. Competitive games, pitch time, and the occasional jog keep me grounded outside the terminal.
Fast-paced BR: movement mechanics and team coordination.
Football on the couch: tactics, seasons, and the occasional rage quit.
Tactical FPS: map knowledge, operator synergy, and clutch rounds.
Laps for clarity: low-impact cardio and a reset from the screen.
Pickup matches with friends, the real kind, on grass.
Casual runs and shoot-arounds: competition without the league fees.
Early morning or evening runs to clear the head and stay sharp.
Open to AI engineering, GTM automation consulting, fractional GTM engineering, and senior full-stack platform work.