{ "basics": { "name": "Haroon Jawad", "label": "AI & Full Stack Engineer · Agentic Systems", "email": "haroonjawad6@gmail.com", "url": "https://haroonjawad.com", "location": { "city": "Istanbul", "countryCode": "TR", "region": "Türkiye" }, "summary": "Full stack engineer specialising in agentic AI systems, LLM agents that reason, call tools and take action, plus the RAG pipelines and production APIs behind them. 6+ years shipping web platforms end to end in React, Next.js, TypeScript and Node. Delivered 40+ projects for clients (Top Rated Plus on Upwork, 100% job success) and built AI products solo, including Analytra, an AI analytics SaaS querying 11 live data sources in natural language. Currently lead engineer on a privacy-preserving identity platform serving 100M+ users, which is where the experience with scale, auth and regulated production systems comes from. Available for select freelance and consulting work, and open to senior/lead AI engineering roles.", "profiles": [ { "network": "GitHub", "username": "haroon-jay", "url": "https://github.com/haroon-jay" }, { "network": "LinkedIn", "username": "haroon-jawad-7942151ba", "url": "https://www.linkedin.com/in/haroon-jawad-7942151ba" } ] }, "work": [ { "name": "Private Identity", "position": "Lead Full Stack Engineer", "url": "https://privateid.com/", "location": "Remote", "startDate": "2025-05-01", "endDate": null, "summary": "Enterprise privacy-preserving identity verification; biometric auth via WebAssembly. Lead and mentor a web engineering team of 8, owning architecture decisions and cross-functional delivery across PrivateID's identity verification platform.", "highlights": [ "Architected PrivateID's Orchestration Engine, enabling configurable workflows, dynamic rule evaluation, and automated multi-step verification flows that reduce manual intervention and accelerate customer integrations.", "Built reusable SDKs for face login, liveness detection, enrollment, and deletion; shipped ML-driven features (age estimation, spoof detection, risk scoring) and LLM-powered explanation systems that interpret verification outcomes and guide users through successful retries.", "Enhanced security with browser-based homomorphic encryption and optimized biometric capture performance in WebView environments.", "Support enterprise clients including Google, CVS Health, and Uber, with the platform serving 100M+ users and tens of millions of verification transactions monthly." ] }, { "name": "Private Identity", "position": "Senior Full Stack Engineer", "url": "https://privateid.com/", "location": "Remote", "startDate": "2022-09-01", "endDate": "2025-05-01", "summary": "Built and maintained the Ultrapass Web SDK, WebAssembly-based biometric authentication with Fully Homomorphic Encryption (FHE). No biometric data ever leaves the device; GDPR and CCPA compliant.", "highlights": [ "Shipped the Ultrapass Web SDK backed by a NestJS microservices orchestration layer and a Node/Express/MongoDB backend with native C++ module bindings.", "Implemented OIDC/OAuth 2.0 (PKCE + Authorization Code Grant) for biometric auth flows.", "Co-maintained the open-source SimpleWebAuthn monorepo (WebAuthn/FIDO2).", "Built the AWS monitoring dashboard (Terraform IaC, Doppler secrets management, GitHub Actions CI/CD) and the PrivateID developer documentation site (Next.js, MDX, FlexSearch full-text search)." ] }, { "name": "Atentiv LLC", "position": "React Developer", "url": "https://www.linkedin.com/company/atentiv-llc", "location": "Full-time", "startDate": "2021-09-01", "endDate": "2022-09-01", "summary": "ADHD digital therapeutic platform. Built and maintained the Patient Management Portal with full role-based access control.", "highlights": [ "Built the Patient Management Portal with React, Redux, Next.js, NestJS, TypeORM, and PostgreSQL, with full RBAC across patient, caregiver, physician, and admin roles.", "Implemented real-time D3.js data visualization for patient monitoring, delivered as reusable React components powering the platform's analytics." ] }, { "name": "Jslytics", "position": "JavaScript Developer", "url": "https://www.jslytics.com", "location": "Contract / Part-time", "startDate": "2020-03-01", "endDate": "2021-09-01", "summary": "Analytics and marketing technology. Built server-side tagging and data-transformation solutions for enterprise clients.", "highlights": [ "Built server-side Google Tag Manager tagging solutions and custom JavaScript variables to capture and transform user data before it reached analytics platforms.", "Configured consent management for GTM deployments, keeping client-side data collection compliant across regions.", "Integrated HubSpot, Salesforce, and Zapier to drive data-backed improvements to client conversion rates." ] }, { "name": "Freelance (Upwork)", "position": "Full Stack Developer", "url": "https://www.upwork.com", "location": "Remote", "startDate": "2019-09-01", "endDate": "2021-03-01", "summary": "Top Rated Plus · 100% Job Success Score · $100K+ earned · 44 jobs · 3,396 hours.", "highlights": [ "Delivered 40+ projects, including several large-scale enterprise engagements (e.g., Bondbury), across e-commerce, healthcare, marketing, and edtech using React, Next.js, Node.js, TypeScript, Firebase, and MongoDB.", "Achieved Top Rated Plus status (top 3% globally) with a 100% job success score." ] } ], "education": [ { "institution": "NUST, National University of Sciences and Technology", "area": "Software Engineering", "studyType": "BSc", "url": "https://nust.edu.pk/" } ], "skills": [ { "name": "Frontend", "keywords": [ "React", "Next.js", "TypeScript", "Tailwind CSS", "D3.js", "WebAssembly" ] }, { "name": "Backend", "keywords": [ "Node.js", "NestJS", "Express", "REST APIs", "GraphQL", "Python" ] }, { "name": "AI / LLM", "keywords": [ "LangChain", "LangGraph", "CrewAI", "RAG", "pgvector", "MCP servers", "Claude SDK", "OpenAI", "Gemini" ] }, { "name": "Databases", "keywords": [ "PostgreSQL", "MongoDB", "Supabase", "Firebase", "Prisma", "Redis" ] }, { "name": "DevOps", "keywords": [ "AWS (S3, CloudFront, SQS, Route53)", "Docker", "Terraform", "GitHub Actions", "Vercel" ] }, { "name": "Auth", "keywords": [ "OIDC", "OAuth 2.0", "WebAuthn / FIDO2", "Clerk", "Supabase Auth" ] } ], "projects": [ { "name": "This site, as an MCP server", "description": "Rebuilt haroonjawad.com so an AI agent can use it directly rather than scraping it. Four MCP tools over streamable HTTP (résumé, services, availability, and a brief-intake tool that reaches me), plus a machine-readable JSON résumé and an llms.txt for discovery. One source of truth feeds the tools, the endpoints and the pages, so nothing drifts. The assistant on the site calls those same tools and shows each call as it happens.", "url": "/connect", "links": [ { "label": "Try the assistant", "href": "/chat" }, { "label": "GET /api/resume.json", "href": "/api/resume.json" }, { "label": "Source on GitHub", "href": "https://github.com/Haroon-jay/my-website" } ], "entity": "Live · 4 MCP tools", "keywords": [ "MCP", "Claude SDK", "Next.js 15", "Streaming tool calls", "Agent-readable" ] }, { "name": "Multi-Agent Orchestration", "description": "Five AI models running as a team with separated duties, building a Notion clone unattended across six phases: an orchestrator, a backend dev, a frontend dev, QA, and an adversary whose only job was to break the app. Roles were described in prompts but enforced with file permissions, developers couldn't edit the defect ledger, QA couldn't touch product code, and no model could certify its own fix. Produced 26,132 lines of TypeScript and a 14-entry defect ledger, 13 of which the adversary found.", "url": "/writing/who-verifies-the-verifier", "links": [ { "label": "Source on GitHub", "href": "https://github.com/Haroon-jay/multi-agent-orchestration" } ], "entity": "Open source · 5 models, 6 phases", "keywords": [ "Multi-agent", "Orchestration", "Separation of duties", "TypeScript", "E2E testing" ] }, { "name": "Analytra", "description": "AI-powered analytics SaaS with natural-language querying over 11 live data sources (ad platforms, CRMs, Stripe, web analytics), plus automated AI-generated reports with PDF export. Built solo.", "url": "https://analytra.io", "entity": "Live SaaS · built and shipped solo", "keywords": [ "Next.js", "TypeScript", "Tailwind", "PostgreSQL", "pgvector", "LangChain", "RAG" ] }, { "name": "AI Interchange", "description": "Shared multi-tenant AI platform powering multiple AI products: centralized billing (Stripe, custom credit wallets), cross-application authentication, a multi-model AI chat app, and a master user system letting one account move across apps under a single sign-on and shared wallet.", "entity": "Flywheel AI (private)", "keywords": [ "Multi-tenant", "Stripe", "Supabase", "Clerk", "Multi-model AI" ] }, { "name": "Workout Form Coach", "description": "Real-time exercise form correction app. Trained an LSTM model on MediaPipe pose-tracking data to detect exercises (bicep curls, squats, pushups) and score form against joint-angle ranges defined with fitness experts, with live feedback and workout summaries.", "url": "https://www.linkedin.com/posts/haroon-jawad-7942151ba_after-6-months-of-building-tweaking-and-ugcPost-7360239400007417856-f7sa/", "urlLabel": "See the demo", "entity": "Personal project · 6 months in the making", "keywords": [ "LSTM", "MediaPipe", "Pose tracking", "Computer vision" ] } ], "certificates": [ { "name": "Model Context Protocol: Advanced Topics", "issuer": "Anthropic", "url": "https://verify.skilljar.com/c/pw9z6ogb2ten" }, { "name": "Building with the Claude API", "issuer": "Anthropic", "url": "https://verify.skilljar.com/c/gygpqi9td987" }, { "name": "Claude Code in Action", "issuer": "Anthropic", "url": "https://verify.skilljar.com/c/crh5gxwct72d" } ], "writing": { "summary": "Technical essays on production AI systems, published on LinkedIn. Writes on agent security, production LLM cost optimization, and AI-native engineering practice.", "highlights": [ "Essay on AI agent deployment security reached 13,500+ readers.", "Essay on hiring for AI-collaborative engineering reached 8,800+ readers." ] }, "proofPoints": [ { "claim": "Cut a production LLM bill by ~80%", "detail": "Model-tier routing (classification off the expensive model), fixing prompt caching that was being invalidated on every call, and stopping whole conversation histories being replayed, without removing a feature or degrading output." }, { "claim": "Upwork: Top Rated Plus, 100% Job Success", "detail": "40+ projects delivered across e-commerce, healthcare, marketing and edtech. 44 jobs · 3,396 hours · $100K+ earned." }, { "claim": "Built and launched a live AI analytics SaaS", "detail": "Analytra, a live product doing natural-language querying over 11 live data sources, with a pgvector RAG pipeline and automated AI reports. Architected, built and shipped end to end alone.", "verifyUrl": "https://analytra.io" }, { "claim": "Open-source contributor: SimpleWebAuthn", "detail": "Co-maintained the SimpleWebAuthn monorepo (WebAuthn/FIDO2).", "verifyUrl": "https://github.com/MasterKale/SimpleWebAuthn" }, { "claim": "13,500+ readers on a single technical essay", "detail": "On hardening autonomous agents that have real system access; a second piece, on why coding interviews test the wrong thing now, reached 8,800+.", "verifyUrl": "https://haroonjawad.com/writing" }, { "claim": "Production experience at 100M+ user scale", "detail": "Lead engineer on a privacy-preserving identity platform used by Google, CVS Health and Uber, where the depth in auth, browser cryptography and regulated production systems comes from.", "verifyUrl": "https://privateid.com/" }, { "claim": "Anthropic-certified on MCP and the Claude API", "detail": "Model Context Protocol: Advanced Topics · Building with the Claude API · Claude Code in Action, all three independently verifiable.", "verifyUrl": "https://verify.skilljar.com/c/pw9z6ogb2ten" } ], "contact": { "email": "haroonjawad6@gmail.com", "github": "https://github.com/haroon-jay", "linkedin": "https://www.linkedin.com/in/haroon-jawad-7942151ba", "endpoints": { "mcp": "https://haroonjawad.com/api/mcp", "resumeJson": "https://haroonjawad.com/api/resume.json", "hire": "https://haroonjawad.com/api/hire", "connect": "https://haroonjawad.com/connect" } }, "meta": { "version": "v1.0.0", "canonical": "https://haroonjawad.com/api/resume.json", "lastUpdated": "2026-08-13", "source": "https://github.com/Haroon-jay/my-website" }, "services": [ { "name": "Agentic AI systems", "description": "Design and build LLM agents that reason, plan, call tools, and take action in production, not demos. LangGraph/LangChain orchestration, tool-calling, evaluation, and cost control.", "deliverables": [ "Agent architecture and orchestration graph", "Tool/function-calling layer against your real systems", "Observability, tracing, and evaluation harness", "Deployment with cost and latency budgets" ], "engagement": "Project-based or fractional lead engineer" }, { "name": "RAG pipelines over your own data", "description": "Retrieval-augmented systems that give grounded, cited answers over unstructured document sets. Chunking strategy, embeddings, pgvector, retrieval quality measurement.", "deliverables": [ "Ingestion and chunking pipeline", "Vector store setup (pgvector/Supabase) and retrieval tuning", "Grounded answer layer with citations", "Retrieval-quality benchmarks before/after" ], "engagement": "Project-based" }, { "name": "AI-native full-stack product build", "description": "End-to-end product delivery where the AI is the product: Next.js/TypeScript front end, Node/NestJS services, PostgreSQL, auth, billing, and the model layer wired together.", "deliverables": [ "Production Next.js + TypeScript application", "API/services layer and data model", "Auth (OIDC/OAuth 2.0/WebAuthn) and billing integration", "CI/CD and infrastructure" ], "engagement": "Project-based or ongoing" }, { "name": "AI cost audit", "description": "A fixed-scope review of what your LLM features actually cost to run. Most teams are paying several times more than they need to, and the causes are boringly consistent: whole conversation histories replayed on every call, prompt caching that looks enabled but never hits, and the most expensive model doing work a cheap one does just as well. Applying exactly this took one production bill down by ~80%.", "deliverables": [ "Where the spend actually goes, broken down by feature and call path", "Prompt-caching audit, what invalidates the cache and the fix", "Model-routing plan: which tasks belong on which tier", "Prioritised changes, each with its projected saving", "Before/after monitoring so the saving is verifiable, not claimed" ], "engagement": "Fixed scope, roughly two weeks" }, { "name": "Agent-readiness & AEO", "description": "Two sides of one problem: being usable by AI agents, and being recommended when someone asks ChatGPT, Claude or Perplexity instead of Google. Neither is SEO. Answer engines quote sources they can parse, verify and attribute, and agents want a tool call rather than a page to scrape, so the work is structuring your capability and content for machine readers. This site is the worked example.", "deliverables": [ "Audit of how agents and answer engines currently see, quote and attribute you", "MCP server exposing your product as typed tools, plus registry listing", "llms.txt, structured data and machine-readable JSON endpoints", "Content restructured into extractable, citable answers", "Re-check afterwards, so the change is measured rather than assumed" ], "engagement": "Fixed scope, or ongoing alongside content work" } ], "availability": { "status": "open", "headline": "Available for AI and full-stack engineering work, agentic systems, RAG pipelines, and production product builds.", "detail": "Takes on a focused number of engagements at a time, so each client gets senior attention rather than a slice of it. Engagements typically start with a short scoping call and end with something shipped and handed over. Also open to senior and lead AI engineering roles.", "openTo": [ "Building agentic AI systems and RAG pipelines end to end", "Fractional lead-engineer work on AI products", "Senior and lead AI engineering roles" ], "roles": [ { "title": "Full Stack Engineer", "pitch": "Ships the whole thing: React and Next.js front ends, Node and NestJS services, PostgreSQL and MongoDB, auth and billing wired in. Six years and 40+ delivered projects of doing exactly this." }, { "title": "AI Automation Specialist", "pitch": "Turns manual, judgement-heavy workflows into agent-driven ones, tool-calling agents, RAG over internal documents, and the evaluation and cost controls that keep them trustworthy in production." }, { "title": "Product Engineer", "pitch": "Owns a product surface end to end: scoping with stakeholders, building it, shipping it, then changing it based on what real usage says. Comfortable being the person accountable for the outcome, not just the ticket." }, { "title": "Forward Deployed Engineer", "pitch": "Sits with the customer and makes the platform work in their environment. Has done this for Google, CVS Health and Uber, integrations, custom workflows, and turning what breaks in the field into product changes." } ], "responseTime": "Usually within 1–2 business days", "timezone": "UTC+3, overlaps a full working day with Europe and the US morning", "bestContact": "Send a brief via the book_intro MCP tool, https://haroonjawad.com/api/hire, or email haroonjawad6@gmail.com" } }