Looking for a job

Hamza Khan

@hamzakhan18

Message

Senior AI Engineer building RAG, multi-agent platforms, and scalable full-stack SaaS.

Pakistan

Message

What I'm looking for

I’m looking for remote contract or full-time work where I can build AI-native SaaS—RAG systems, multi-agent workflows, and LLM integrations—supported by scalable backend architecture, microservices, and reliable deployments in production.

I’m a Senior AI Engineer and Full-Stack Developer with 12 years of production experience building backend systems, AI-enabled platforms, and full-stack SaaS products. I specialize in AI-native architectures—RAG pipelines, multi-agent workflows, and LLM integrations—along with the backend infrastructure that makes them reliable at scale.

My strongest work lives at the intersection of AI/LLM engineering and backend systems: OpenAI and Anthropic Claude integrations, LangChain and LlamaIndex workflows, and vector database-driven retrieval using Pinecone, pgvector, and Weaviate. I design production systems using Node.js, TypeScript, Python, FastAPI, and PostgreSQL, and I build microservices and event-driven APIs that can handle real-world load.

I’ve designed, built, and deployed production-scale solutions across HealthTech, FinTech, MarTech, Renewable Energy, Real Estate, and HRTech. From agent orchestration platforms and RAG layers to HIPAA-compliant communications and AI-enabled operations dashboards, my focus stays consistent: scalable architecture, clean execution, and measurable outcomes.

Experience

Work history, roles, and key accomplishments

Current

Principal Software Engineer

Current

Bit & Bytes LLC

Apr 2024 - Present (2 years 1 month)

Architected AI-native SaaS platforms — RAG systems, multi-agent workflows, LLM integrations — across 12+ production deployments serving 50,000+ users. Led system design and microservices using Node.js, TypeScript, FastAPI, React, Next.js. Reduced LLM operational costs by 40% and improved API response times by 80% through query optimisation. 12 years senior engineering.

LLM Integrations Node TypeScript fastAPI Microservices React Next.js AWS

Senior Full-Stack Software Engineer

Rolustech

Jan 2022 - Mar 2024 (2 years 2 months)

Delivered scalable platforms across automotive, healthcare, and real-estate verticals serving 10,000+ users. Built Dockerised microservices and reduced deployment time by 70% via CI/CD using GitHub Actions and Terraform. Mentored 5+ engineers across cross-functional teams.

gRPC Redis MongoDB Docker Microservices AWS CI CD GitHub Actions Terraform Mentoring

Senior Software Engineer/AI Systems Lead

59pines

Apr 2020 - Jan 2022 (1 year 9 months)

Developed document AI systems, NLP chatbots, and predictive analytics platforms processing 100,000+ documents monthly. Designed backend services with Django, Celery, and PostgreSQL, and deployed serverless automation pipelines on AWS — reducing manual processing time by 80%.

NLP Predictive Analytics Django Celery PostgreSQL Serverless AWS

Software Engineer

PureLogics

Feb 2016 - Mar 2020 (4 years 1 month)

Built scalable backend services and full-stack applications across multiple domains, including analytics dashboards and production integrations serving 20,000+ users. Improved performance, observability, and system reliability — cutting page load times by 55% and reducing critical incidents by 30% across releases.

API Development Backend Engineering Full Stack Dashboards Performance Optimization Observability Debugging System Reliability

Software Engineer

PureLogics

Aug 2014 - Jan 2016 (1 year 5 months)

Developed APIs and database-driven applications with focus on system design, debugging, and performance optimisation. Built backend foundations supporting 50,000+ users across production systems, with 99.9% uptime and 60% faster query response times through optimisation.

API Development System Design Debugging Performance Optimization Backend Engineering DataBase Systems Reliability Engineering Engineering Best Practices