09/04/2026 updated
100 % available
AI Engineer | LLM Applications, RAG & Autonomous Agents
Hafizabad, Pakistan
Only remote
BS Computer ScienceAbout me
I build and ship production AI applications for real businesses: LLM agents, RAG, and automations. Founder of LiveAssist, an AI assistant SaaS. I own problems from scope to deployment and move fast with AI coding tools.
OpenAIDevOpsPython (Programming Language)FlaskPrompt Engineering
LLM Application Development & RAG
Expertise in building production-ready LLM agents that interpret user intent, retrieve context via RAG, call tools, and complete multi-step tasks. Proficiency with vector search technologies such as pgvector and Pinecone, multi-LLM orchestration and failover across OpenAI, Anthropic, and Google Gemini, as well as prompt engineering, structured outputs, evals, and observability.
Backend Engineering with Python & Flask
Strong command of Python-based backend development using Flask, REST APIs, webhooks, OAuth, SQL, and asynchronous task processing with Celery and Redis. Experience building scalable, real-time systems with SocketIO and integrating third-party APIs for billing, scheduling, and authentication.
Cloud Infrastructure & DevOps
Hands-on experience with containerization using Docker and docker-compose, CI/CD pipelines via GitHub Actions, and cloud deployment on platforms such as Northflank, Railway, and Render. Familiarity with PostgreSQL including pgvector, Alembic migrations, Pinecone, Gunicorn, and Linux environments.
AI-Assisted Development
Daily use of AI coding agents including Claude Code and Codex for scoping, implementation, and debugging, as well as MCP and Git-based workflows for efficient solo development.
Guardrails & Human-in-the-Loop Systems
Implementation of guardrails and human-in-the-loop handoff mechanisms, plus logging and observability tooling to diagnose agent failures and fix failure modes in production.
LangChain & Orchestration Frameworks
Practical experience with LangChain for building and orchestrating LLM-powered pipelines and agent workflows in production SaaS environments.
Technical Recruiting & Stakeholder Communication
Over 4 years in client-facing roles for technology companies, screening engineering candidates, translating technical requirements, and communicating clearly with both technical and non-technical stakeholders across time zones.
Network Infrastructure & Support
Background in monitoring and troubleshooting Cisco-based ISP network infrastructure with NOC teams, grounded in CCNA/CCNP foundational knowledge.
Expertise in building production-ready LLM agents that interpret user intent, retrieve context via RAG, call tools, and complete multi-step tasks. Proficiency with vector search technologies such as pgvector and Pinecone, multi-LLM orchestration and failover across OpenAI, Anthropic, and Google Gemini, as well as prompt engineering, structured outputs, evals, and observability.
Backend Engineering with Python & Flask
Strong command of Python-based backend development using Flask, REST APIs, webhooks, OAuth, SQL, and asynchronous task processing with Celery and Redis. Experience building scalable, real-time systems with SocketIO and integrating third-party APIs for billing, scheduling, and authentication.
Cloud Infrastructure & DevOps
Hands-on experience with containerization using Docker and docker-compose, CI/CD pipelines via GitHub Actions, and cloud deployment on platforms such as Northflank, Railway, and Render. Familiarity with PostgreSQL including pgvector, Alembic migrations, Pinecone, Gunicorn, and Linux environments.
AI-Assisted Development
Daily use of AI coding agents including Claude Code and Codex for scoping, implementation, and debugging, as well as MCP and Git-based workflows for efficient solo development.
Guardrails & Human-in-the-Loop Systems
Implementation of guardrails and human-in-the-loop handoff mechanisms, plus logging and observability tooling to diagnose agent failures and fix failure modes in production.
LangChain & Orchestration Frameworks
Practical experience with LangChain for building and orchestrating LLM-powered pipelines and agent workflows in production SaaS environments.
Technical Recruiting & Stakeholder Communication
Over 4 years in client-facing roles for technology companies, screening engineering candidates, translating technical requirements, and communicating clearly with both technical and non-technical stakeholders across time zones.
Network Infrastructure & Support
Background in monitoring and troubleshooting Cisco-based ISP network infrastructure with NOC teams, grounded in CCNA/CCNP foundational knowledge.
Experience
Professional experience0 - 5 years
Freelancer since2020
Languages
EnglishFluent
Project history
Built and operated a multi-tenant AI assistant SaaS platform running in production. Developed an LLM agent that interprets user intent, retrieves operational context from each client's knowledge base via RAG, calls tools and integrations, and completes multi-step tasks. Engineered a multi-LLM setup with OpenAI, Anthropic, and Google Gemini with automatic failover. Implemented retrieval with pgvector and Pinecone vector search, structured-output processing with schema validation and retries, guardrails, human-in-the-loop handoff, logging, and observability. Integrated third-party APIs and webhooks including Stripe billing, scheduling, and OAuth. Runs on Flask, PostgreSQL, Celery/Redis, and Docker with automated builds and backups via GitHub Actions CI/CD.
4+ years in client-facing roles for technology companies with clear communication across technical and non-technical stakeholders across time zones. Screened engineering candidates and translated technical requirements, building strong fluency with SaaS teams and developer workflows. Served UK and EU clients remotely.
Monitored and troubleshot Cisco-based ISP network infrastructure with the NOC team, with a foundation in CCNA/CCNP. Based in Lahore, Pakistan.