Looks like you have JavaScript disabled. For the full Twine experience, you will need to re-enable it.

Hi, I’m Waleed Shoaib, an AI Engineer with 3+ years of experience designing, building, and deploying LLM-powered systems, agentic workflows, and Retrieval-Augmented Generation (RAG) pipelines in production. I have a strong track record delivering financial and healthcare AI solutions, real-time ETL pipelines, vector and graph databases, and cloud-native deployments on GCP and AWS. I enjoy architecting robust systems, evaluating models, and optimizing performance to provide reliable, scalable AI capabilities. Beyond coding, I collaborate with product and data teams to design maintainable architectures, implement thorough monitoring, and iterate on memory and retrieval strategies to improve contextual coherence and result quality. I’m passionate about delivering practical, production-ready AI that delivers real value to users and stakeholders.…Hi, I’m Waleed Shoaib, an AI Engineer with 3+ years of experience designing, building, and deploying LLM-powered systems, agentic workflows, and Retrieval-Augmented Generation (RAG) pipelines in production. I have a strong track record delivering financial and healthcare AI solutions, real-time ETL pipelines, vector and graph databases, and cloud-native deployments on GCP and AWS. I enjoy architecting robust systems, evaluating models, and optimizing performance to provide reliable, scalable AI capabilities. Beyond coding, I collaborate with product and data teams to design maintainable architectures, implement thorough monitoring, and iterate on memory and retrieval strategies to improve contextual coherence and result quality. I’m passionate about delivering practical, production-ready AI that delivers real value to users and stakeholders.

Waleed Shoaib

Full Stack Developer, Back-End Developer, Web Developer, +4





Hi, I’m Waleed Shoaib, an AI Engineer with 3+ years of experience designing, building, and deploying LLM-powered systems, agentic workflows, and Retrieval-Augmented Generation (RAG) pipelines in production. I have a strong track record delivering financial and healthcare AI solutions, real-time ETL pipelines, vector and graph databases, and cloud-native deployments on GCP and AWS. I enjoy architecting robust systems, evaluating models, and optimizing performance to provide reliable, scalable AI capabilities. Beyond coding, I collaborate with product and data teams to design maintainable architectures, implement thorough monitoring, and iterate on memory and retrieval strategies to improve contextual coherence and result quality. I’m passionate about delivering practical, production-ready AI that delivers real value to users and stakeholders.…Hi, I’m Waleed Shoaib, an AI Engineer with 3+ years of experience designing, building, and deploying LLM-powered systems, agentic workflows, and Retrieval-Augmented Generation (RAG) pipelines in production. I have a strong track record delivering financial and healthcare AI solutions, real-time ETL pipelines, vector and graph databases, and cloud-native deployments on GCP and AWS. I enjoy architecting robust systems, evaluating models, and optimizing performance to provide reliable, scalable AI capabilities. Beyond coding, I collaborate with product and data teams to design maintainable architectures, implement thorough monitoring, and iterate on memory and retrieval strategies to improve contextual coherence and result quality. I’m passionate about delivering practical, production-ready AI that delivers real value to users and stakeholders.

Available to hire

Hi, I’m Waleed Shoaib, an AI Engineer with 3+ years of experience designing, building, and deploying LLM-powered systems, agentic workflows, and Retrieval-Augmented Generation (RAG) pipelines in production. I have a strong track record delivering financial and healthcare AI solutions, real-time ETL pipelines, vector and graph databases, and cloud-native deployments on GCP and AWS. I enjoy architecting robust systems, evaluating models, and optimizing performance to provide reliable, scalable AI capabilities.

Beyond coding, I collaborate with product and data teams to design maintainable architectures, implement thorough monitoring, and iterate on memory and retrieval strategies to improve contextual coherence and result quality. I’m passionate about delivering practical, production-ready AI that delivers real value to users and stakeholders.

Skills

Experience Level

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Intermediate

PHP

Intermediate

Work Experience

AI Engineer at Aeyron

May 1, 2025 - November 27, 2025

Architected end-to-end agentic workflows using LlamaIndex and ReAct frameworks for task automation and decision-making. Built a Daily Forex Algorithmic Agent ingesting data from FMP API, Yahoo Finance, and news sources with ClickHouse; designed real-time ETL pipelines with under 500ms latency; integrated OpenAI function-calling and LangChain tools to autonomously trigger analysis, visualize results, and report trading sentiment using FinBERT embeddings. Implemented multi-agent collaboration, improving analysis accuracy and throughput by 35%. Built advanced RAG pipelines with Milvus for semantic retrieval of economic documents and contextual reasoning. Deployed monitoring dashboards with Prometheus and Grafana to track latency and query performance.

AI Engineer at Catalic AI

May 1, 2025 - May 1, 2025

Led ETL pipeline development for FOMC datasets, optimizing data flow for financial analysis (10% reduction in processing time). Developed a Research Agent (LlamaIndex, ReAct) to automate information gathering and analysis from diverse sources, improving research efficiency (15% improvement). Implemented ReAct memory management (Long-Term, Semantic) to enhance contextual understanding, reducing irrelevant information retrieval (10% reduction). Integrated Milvus DB for vector embeddings and efficient semantic search. Leveraged Memgraph and FinBERT for NLP and sentiment analysis of FOMC transcripts, extracting key insights via NER. Developed automated Prompt Engineering system (HALU Eval, DeepEval) to evaluate and refine prompts, increasing effectiveness by 5-10%. Deployed cloud-native solutions (Terraform, ArgoCD, GCP: Cloud Storage, Pub/Sub) for scalable AI deployments. Monitored system performance with Prometheus and Grafana.

Software Engineer at Objex

February 1, 2025 - February 1, 2025

Developed and maintained the social media platform Rabbito using microservices on Google Cloud Platform for scalability and reliability. Implemented Retrieval-Augmented Generation (RAG) with Firestore for vector storage and retrieval, enhancing search and recommendations by 40%. Built and optimized scalable GraphQL APIs and secure authentication workflows using OAuth2 and Firebase Authentication. Designed and deployed AWS API Gateway for microservices routing, load balancing, and secure communication. Integrated Google Cloud Pub/Sub for real-time data pipelines; automated workflows with Cloud Scheduler; implemented logging with Google Cloud Logging and Firestore monitoring tools. Integrated third-party APIs (Facebook Graph API, LinkedIn API, YouTube API) to enhance social data capabilities. Implemented an ActivityPub server for decentralized networking and improved collaboration (Jira, Slack).

Backend Developer at Eastlancer

February 1, 2024 - February 1, 2024

Developed scalable backend APIs using Node.js and Express.js; integrated Cloudinary for image storage; designed RESTful APIs; enhanced real-time communications through WebSockets (Socket.IO); optimized performance via caching and load balancing.

Software Engineer at Objex

March 1, 2024 - February 28, 2025

Developed and maintained a cloud-native, microservices-based platform on Google Cloud Platform (GCP). Integrated Retrieval-Augmented Generation (RAG) components using Firestore for vector storage, improving search and recommendation capabilities by 40%. Designed and optimized GraphQL APIs, reducing query latency by 25% through schema and resolver-level optimizations. Built event-driven data pipelines using Google Cloud Pub/Sub and schedulers to support real-time and asynchronous processing. Implemented authentication, observability, and logging using OAuth2, Firebase Authentication, and Google Cloud Logging to improve system security and operational visibility.

Software Engineer at Eastlancer

March 1, 2023 - February 29, 2024

Built and maintained scalable backend APIs using Node.js and Express, supporting data-driven application features. Integrated AI-assisted services and third-party APIs into backend workflows, enabling intelligent data processing and automation. Improved system performance and reliability through caching, load balancing, and efficient real-time communication patterns.