Malik Akhtar · AI developer & software engineer
Karachi, Pakistan · UTC+5
I build AI agents, LLM apps, and the API integrations that make them work in production.
10 years of software engineering; the last few shipping LLM systems into real business software. Not a chatbot that answers and stops.
- 10 years of software engineering
- 210+ projects · 5.0 average rating, before Upwork
- Replies to new enquiries within 24 hours
Pick a problem. This is the shape of the read I'd send back within 24 hours.
RE: Invoices & documents
- Approach
- Read the invoice, check it against your own systems, do the work: a bill in QuickBooks, a ticket in the helpdesk, a line in Slack.
- What breaks
- 429s, 5xx, timeouts — so retry with exponential backoff, duplicate and reconciliation checks, an approval threshold, and a replayable event log.
- Not AI
- I tell you when AI is the wrong tool. Sometimes a 40-line script beats an LLM: cheaper, faster, deterministic.
RE: CRM ↔ accounting sync
- Approach
- Two systems never designed to talk: webhooks, OAuth flows, rate-limited endpoints. Refunds, partial payments, and reconciliation handled automatically.
- What breaks
- Rate-limited endpoints and OAuth flows. Error handling, logging, and monitoring from day one, not after something breaks.
- Not AI
- Sometimes a 40-line script beats an LLM: cheaper, faster, deterministic. I say so even when the AI version would bill more hours.
- Proof
- Stripe ↔ QuickBooks sync for a logistics company. Has reconciled cleanly since launch without manual fixes.
RE: An assistant on your own data
- Approach
- Trained on your own data — Slack, Notion, Google Workspace, or your database — and answering with sources, so output is verifiable instead of confidently wrong.
- What breaks
- Confidently wrong answers. Sources on every answer make them verifiable; error handling, logging, and monitoring from day one, not after something breaks.
- Not AI
- I tell you when AI is the wrong tool. I say so even when the AI version would bill more hours.
- Tools
- Anthropic API · OpenAI API · open models · LangChain · LlamaIndex · RAG · Pinecone · Supabase pgvector · Chroma · evals
RE: An undocumented or legacy API
- Approach
- Third-party, undocumented, and legacy SOAP APIs: webhooks, OAuth flows, rate-limited endpoints. Half my career. Built to survive production, not just a demo.
- What breaks
- Rate-limited endpoints, OAuth flows, SOAP. Error handling, logging, and monitoring from day one, not after something breaks.
- Not AI
- Sometimes a 40-line script beats an LLM: cheaper, faster, deterministic. Either way, code you can hand to another developer: documented, structured, yours.
- Tools
- REST · GraphQL · webhooks · OAuth2 · SOAP · Python (FastAPI, Django) · Node.js (Express, NestJS) · PHP/Laravel · .NET/C#
- Timeline & cost
- Realistic estimates. Fixed scope, clear milestones, no surprise invoices.
Work
One you can open. Two I can only describe.
-
Relay
Paper in. Actions out.
An AI operations agent that reads supplier invoices and customer emails, checks them against the company's own systems, and does the work: bills in QuickBooks, tickets in the helpdesk, a line in Slack.
- Six tools with strict JSON schemas
- Duplicate and reconciliation checks
- Approval threshold
- Retry with exponential backoff for 429 / 5xx / timeouts
- Event log streamed over SSE — replayable, testable without a network
Python · FastAPI · LLM tool use · SSE · vanilla JS · pytest
Open Relay -
· Client work · Logistics company
Stripe ↔ QuickBooks sync
Refunds, partial payments, and reconciliation handled automatically. Has reconciled cleanly since launch without manual fixes.
No public link — client work
-
· Personal tooling
AI job-matching pipeline
Fetches listings, scores them against a profile, drafts proposals with an LLM, schedules follow-ups. FastAPI + SQLite + local dashboard, tested end to end.
No public link — personal tooling
What I build
Systems that do the work. Not a chatbot that answers and stops.
AI agents & automation
Systems that do the work: process documents, qualify leads, research, draft, classify, and take real actions inside your tools. Not a chatbot that answers and stops.
AI inside your existing stack
LLMs wired into your CRM, database, admin panel, Google Workspace, Slack, Notion, HubSpot, Shopify, or a legacy system nobody wants to touch.
Complex API integration
Third-party, undocumented, and legacy SOAP APIs. Webhooks, OAuth flows, rate-limited endpoints, data syncs between systems never designed to talk.
Half my career.RAG chatbots & assistants
Trained on your own data, answering with sources so output is verifiable instead of confidently wrong.
Backend & workflow systems
The APIs, queues, schedulers, and pipelines underneath all of the above. Built to survive production, not just a demo.
Email infrastructure & deliverability
Multi-domain sending, SPF/DKIM/DMARC, custom tracking domains, warmup, API-level integration.
What 10 years buys you
- I tell you when AI is the wrong tool. Sometimes a 40-line script beats an LLM: cheaper, faster, deterministic. I say so even when the AI version would bill more hours.
- Error handling, logging, and monitoring from day one, not after something breaks.
- Realistic estimates. I have been wrong enough times to know how long things take.
- Code you can hand to another developer: documented, structured, yours. No lock-in, no black box.
How I work
- Short scoping call first. I would rather tell you the project is simpler than you thought than take a bloated budget.
- Fixed scope, clear milestones, no surprise invoices.
- Regular written updates. You never have to ask what the status is.
- Support after delivery. I don't disappear at handover.
Stack
The tools I reach for, and the older ones I still add AI to.
- AI / LLM
- Anthropic API · OpenAI API · open models · LangChain · LlamaIndex · RAG · vector databases (Pinecone, Supabase pgvector, Chroma) · function calling / tool use · MCP servers · prompt engineering · evals
- Backend
- Python (FastAPI, Django) · Node.js (Express, NestJS)
- Frontend
- React · Next.js · TypeScript
- Data & infra
- PostgreSQL · MySQL · MongoDB · Redis · Docker · AWS · CI/CD
- Integration
- REST · GraphQL · webhooks · OAuth2 · SOAP · Stripe · Twilio · HubSpot · Shopify · n8n · Make · Zapier
- Also
- PHP/Laravel · .NET/C# — for adding AI to systems that already exist
Within 24 hours: an honest read on approach, timeline, cost.
Send me the problem. Short scoping call first — I would rather tell you the project is simpler than you thought than take a bloated budget.