wasim.RANJHA / ENGINEERLet’s talk
AVAILABLE FOR FREELANCE & COLLABORATIONS

AI & web apps.
Built for your
business.

I’m Wasim Ranjha, your Python & AI developer. I help businesses automate repetitive work, handle customer calls, and turn product ideas into working software.

Discuss your project See my projects

Work directly with me · Agree on scope before development

5+Years building solutions
23Projects to explore
End to endFrom idea to deployment
Wasim Ranjha reimagined as a white and copper cyborg
PythonDjangoFastAPIReactPostgreSQLAWSDockerQdrantPlaywright
01 / SELECTED WORK

Software, built
for real work.

Explore the problem behind each project, what I built, and the workflow it supports. Open a project for screenshots and implementation details.

Showing 3 of 23 projects

AI Voice Agent01

A multi-industry AI receptionist platform. Businesses create an account, get a phone number, and connect an AI assistant to handle incoming calls.

What I builtFrom account signup to an AI-powered business phone number in one platform.

Built for: Clinics, real estate & home services

The challenge
Service businesses need to answer calls while their teams are busy with customers or jobs.
Designed to
Let businesses delegate incoming call handling to an AI assistant on their own phone number.
AI Automation02

A tool that breaks a goal into tasks and coordinates AI agents to work through them.

What I builtGoal planning and coordinated AI task execution in one application.

Built for: People planning complex tasks

The challenge
A broad goal still needs to become a workable sequence of tasks.
Designed to
Move from a goal to an actionable plan and coordinated AI execution.
AI SaaS03

A web application for reviewing property listings and generating analysis reports.

What I builtProperty listing evaluation, market information, and report generation in one workflow.

Built for: Property research

The challenge
Property research means bringing listing details, market information, and analysis together.
Designed to
Bring property evaluation and report generation into one research workflow.
WHAT I DO

The right help.
For your next
build.

One developer for the technical work.
A small specialist team when your project needs more.

Not sure where to start?Let’s talk
Wasim RanjhaPython & AI full-stack developer
01

AI agents & automation

Phone agents, chat assistants, and search tools connected to your documents and business software.

Python / FastAPI / RAG

Give routine calls, questions, and document searches a better workflow.

I build voice agents, chat assistants, and search tools connected to your business data. We start with one specific task and decide where a person should stay in control.

What’s included

  • Voice or chat workflows matched to your business
  • Answers grounded in your documents and knowledge base
  • Connections to the tools your team already uses
  • Testing, deployment, and a documented handover

Where we’ll start

  • Which questions or tasks come up most often?
  • What information can the assistant access?
  • When should the assistant hand over to a person?

Python · FastAPI · RAG · Twilio · Vapi

Discuss this service
02

Web apps & SaaS

Customer portals, internal tools, and SaaS products. Frontend, backend, and deployment handled together.

React / Python / Django

Build the product your customers and team actually need.

I work on both sides of a web application: the interface people use and the backend that keeps it running. That can mean a first release, an internal portal, or extending an existing product.

What’s included

  • A responsive interface built around your main workflows
  • Django or FastAPI backend and database design
  • Authentication, roles, and the integrations in your scope
  • Deployment and documentation for your team

Where we’ll start

  • Who will use the application?
  • What must the first release let them do?
  • Are we building from scratch or working with existing code?

React · Python · Django · FastAPI · PostgreSQL

Discuss this service
03

Web scraping & data pipelines

Collect and clean the information you need, then deliver it to your database or team.

Python / Playwright / Selenium

Get useful data without repeating the same research every day.

I build extraction and monitoring tools that collect data from agreed sources, clean it, and deliver it in a format your team can use. The approach depends on the source, update frequency, and access requirements.

What’s included

  • Extraction scripts for the sources in your scope
  • Data cleaning and structured exports
  • Scheduled collection and monitoring where needed
  • Error handling, deployment, and operating instructions

Where we’ll start

  • Which sources and fields do you need?
  • How often should the data update?
  • Where should the results go?

Python · Playwright · Selenium · APIs

Discuss this service
04

Cloud deployment & DevOps

Set up the infrastructure, databases, and deployment process around your application.

AWS / DigitalOcean / Docker

Take your application from a local build to a maintained deployment.

I help configure the infrastructure around your application, including databases, containers, deployment pipelines, and API access. We review the existing setup before choosing what to change.

What’s included

  • A deployment plan for your application
  • Cloud and database configuration
  • Build and deployment automation
  • Handover notes and an agreed support scope

Where we’ll start

  • Where does the application run today?
  • What reliability or scaling problems are you seeing?
  • Who will operate it after handover?

AWS · DigitalOcean · Docker · Linux · CI/CD

Discuss this service
05

Mobile app development

iOS and Android development with my specialist team, supported by the APIs I build.

Flutter / React Native / Mobile UI

Put your product in your customers’ hands.

For mobile projects, I coordinate with my specialist team on the application and work on the backend and integrations it needs. We choose the platform and release scope around your users.

What’s included

  • A defined iOS or Android release scope
  • Mobile screens and core user flows
  • Backend APIs and integrations
  • Testing and release preparation

Where we’ll start

  • Do you need Android, iOS, or both?
  • Which device features does the app need?
  • Is there an existing backend or design?

Flutter · React Native · Mobile UI · APIs

Discuss this service
06

Design & visual content

Interface design, brand assets, and video production with my creative team.

UI design / Brand identity / Graphics

Give your product a clear, consistent visual identity.

I collaborate with a specialist creative team on interface design, brand assets, and AI-assisted video work. We agree on the deliverables and visual direction before production.

What’s included

  • A visual direction based on your brief
  • Interface, brand, or video assets within the agreed scope
  • Review rounds and refinements
  • Final files in the formats you need

Where we’ll start

  • What are you making, and who is it for?
  • Do you have existing brand guidelines?
  • Which formats and deliverables do you need?

UI design · Brand identity · Graphics · AI video

Discuss this service
03 / ABOUT ME

Wasim Ranjha.
Your development partner.

Also known as Waseem Ranjha · Python & AI full-stack developer

I’ve spent the last five years working with Python, web applications, and more recently, AI systems. I enjoy taking a messy process and turning it into something people can use without thinking twice.

My work covers Django and FastAPI backends, React interfaces, voice agents, and cloud deployments. You’ll work directly with me on the technical decisions and progress.

LinkedInGitHubXInstagramYouTubeFacebook
Off the clock? Soccer, camping, and a good game.
EXPERIENCE
2024 — 2026

Full Stack AI Developer

Angular Quantum

SaaS platforms, voice agents, FastAPI backends, and AWS deployments.

2022 — 2024

Backend Python Developer

Tiksom Limited

Django APIs and React features for applications across multiple industries.

2021 — 2022

Python Developer

NeXskill

Hands-on application development with Django and Flask.

Education & professional training

ICS — Computer Science, Degree College Kot Momin (2018–2020). Professional training and mentorship in Python and backend systems at NeXskill.

04 / WORKING TOGETHER

From the first call
to the final handover.

We agree on the scope first, then work in small, reviewable steps.

01Discover

Start with the problem

Tell me what you need, who will use it, and what isn’t working today.

02Design

Agree on the scope

Agree on a focused scope, architecture, milestones, and estimate before development begins.

03Build

See the progress

I share working versions for you to review, so we can catch issues and adjust early.

04Launch

Test and launch

Test, deploy, and hand over your product with documentation and an agreed support plan.

05 / CLIENT FEEDBACK

Good work starts
with good people.

A few words from the people
I’ve worked with.

Wasim and his team delivered our custom AI RAG platform ahead of schedule. Their deep expertise in Python, FastAPI, and AWS deployments saved us months of engineering effort and provided a robust, highly scalable system.
Ronald BensonCEO at Spector · USA
01 / 04
06 / RATES

Choose a
starting point.

These are my hourly rates. I’ll estimate the work once we’ve discussed your requirements.

Automation setup

Scripts, integrations, and focused automation.

$15/ hour
  • AI workflow planning
  • Custom scraping scripts
  • API integrations & vector indexing
  • 1 month technical support
Discuss your project
WEB APPLICATIONS

Web application development

Web applications, APIs, and a first release.

$19/ hour
  • FastAPI / Django + React
  • RAG search integration
  • AWS deployment
  • 3 months technical support
Discuss your project

Advanced AI development

Voice agents and more complex AI integrations.

$49/ hour
  • Multi-agent and voice AI systems
  • Autoscaling & CI/CD
  • Scraping analytics & database replication
  • 6 months technical support
Discuss your project
07 / TOPICS I WORK WITH

A few things
I’m interested in.

Notes on the decisions behind the code. Open a topic to read more.

01Document searchSearching documents with FastAPI and pgvectorHow a document becomes a useful, traceable answer.
Engineering notes · Wasim Ranjha

Start with the source

A useful document search tool needs more than an upload button. It needs to keep track of where each passage came from, who may read it, and whether the source has changed. I would settle those requirements before choosing a model.

Build retrieval first

A practical starting point is to split documents into passages, store their embeddings alongside source references, and retrieve relevant passages for each question. pgvector adds vector similarity search to PostgreSQL, so the content and its metadata can live together.

Make answers inspectable

Show the source passages with the answer and let the user open the original document. Test with real questions, including questions the documents cannot answer. The useful result is an answer someone can check—not simply fluent text.

pgvector documentation
02AI workflowsCoordinating several AI agentsDecide what each step owns before adding more agents.
Engineering notes · Wasim Ranjha

One workflow before many agents

I would begin by writing down the job in ordinary steps: collect information, check it, prepare a result, and request approval if needed. If a single workflow can do that reliably, adding several agents may only make it harder to debug.

Give each step a contract

For a multi-agent design, define the input and expected output of each step. Keep shared state explicit, record failures, and put limits on retries and execution time. A task should not continue indefinitely because two agents disagree.

Keep consequential actions reviewable

Drafting a response and sending it are different actions. Separate suggestions from changes to external systems, and decide which actions need human review. Start testing with recorded examples before allowing the system to operate on live work.

03Browser automationChoosing between Playwright and SeleniumChoose around the application and team you have.
Engineering notes · Wasim Ranjha

Look at the existing setup

The starting point is the team’s language, browser requirements, and existing automation. A working Selenium suite can be worth extending. For a new project, I would compare a small end-to-end flow in each candidate rather than choose from a feature list alone.

Use meaningful selectors

Playwright’s locators support finding elements by role, label, and other user-facing properties. These are useful when the goal is to interact with the application as a person would. Selectors based only on a long chain of page containers tend to be harder to maintain.

Plan for change

Authentication, slow pages, and layout changes are part of the work. Keep test data separate, capture useful failure information, and make retry behavior deliberate. A script that succeeds once is the beginning, not the finished automation.

Playwright locator documentation
04LLM developmentFine-tuning or prompt engineering?Identify what is failing before choosing how to fix it.
Engineering notes · Wasim Ranjha

Name the problem

An assistant might be missing information, using the wrong format, or making the wrong decision. Those are different problems. I would collect representative examples and define what a good response looks like before changing the system.

Try the smallest useful change

For missing business information, a retrieval step may be worth evaluating. For an inconsistent format, clearer instructions and output validation may be enough. Fine-tuning is a candidate to investigate when a repeatable behavior remains difficult to achieve and suitable training examples are available.

Compare against a baseline

Keep a separate evaluation set and compare quality, cost, and response time. Include difficult and ambiguous cases. The decision should come from those results, with a clear plan for maintaining the chosen approach as requirements change.

05Voice agentsBuilding a multi-industry AI receptionistConnect business signup, phone setup, and incoming calls.
Engineering notes · Wasim Ranjha

Define the call boundaries

Kira supports medical and dental clinics, real estate, plumbing, HVAC, and other business niches. Businesses register an account, get a phone number, and connect an AI assistant to handle incoming calls using Twilio and Vapi. The wider design question is where an automated receptionist should help and where a staff member should take over.

Treat booking as a transaction

For an appointment workflow, I would define how availability is checked, how details are confirmed, and what happens when a booking system is unavailable. The agent should not say an appointment is booked until the connected system confirms it.

Design the handoff

A useful handoff gives staff the caller’s request and the information already collected, within the agreed privacy requirements. Test interrupted speech, corrections, and unsuccessful calls as carefully as the happy path.

Explore Kira
06Data pipelinesRunning Python scrapers at scaleReliable collection starts with limits, validation, and recovery.
Engineering notes · Wasim Ranjha

Agree on the data contract

List the sources, fields, update frequency, and delivery format. Decide how to represent missing values and duplicate records. These choices determine whether the collected data is useful to the team receiving it.

Control the request rate

Request pacing should account for the source and its access requirements. Scrapy’s AutoThrottle adjusts download delays using latency and a target concurrency setting, within configured limits. Whatever framework is used, errors should lead to bounded retries rather than an unlimited request loop.

Watch the output, not just the jobs

A completed job can still contain incomplete or unexpected data. Validate required fields, monitor record counts, and keep enough source context to investigate changes. Save progress so a failure does not require starting every collection again.

Scrapy AutoThrottle documentation
08 / COMMON QUESTIONS

A few things
you might ask.

What can you help me build?

AI voice and chat agents, RAG systems, SaaS products, internal tools, scraping pipelines, and cloud infrastructure. My specialist team also supports mobile development and creative work.

Can you work with our existing tools?

Yes. We start by reviewing your current software and available APIs, then scope the connections your workflow needs. Integration requirements are agreed before development.

How much will my project cost?

Published hourly rates start at $15 for automation, $19 for SaaS development, and $49 for enterprise AI work. The final scope, estimate, timeline, and support are agreed together before kickoff.

What happens after launch?

Handover and support are part of the conversation from the start. The published packages include one, three, or six months of technical support depending on the engagement.

Can we start small?

Absolutely. Bring one process, one product idea, or one technical problem. We can define a focused first release and build on it as your needs become clearer.

CONTACT

Have a project
in mind?

Send me a short description of what you need, even if you haven’t worked out all the details. Email and WhatsApp both work.

What happens next?

  1. I review your goals and ask any missing questions.
  2. We agree on the scope, milestones, and estimate.
  3. You decide whether to move forward.
hello@wasimranjha.com +92 343 6000542Prefer WhatsApp? Let’s chat
START A CONVERSATION

What would you like to build?

No technical brief needed. Start with the problem you want to solve.

Review your brief, then send by email or WhatsApp. Your details stay in this page until you choose how to share them.