Khalid Sayyed

About

I am an AI Software Engineer with 1+ years of professional experience building production-grade Generative AI, full-stack, and scalable backend systems. My work sits at the intersection of AI engineering and software engineering, with a strong focus on turning LLM capabilities into reliable, secure, and scalable enterprise products. At Capgemini, I work on enterprise-scale Generative AI platforms, where I have contributed to end-to-end frontend and backend capabilities including real-time LLM streaming, web search integration, multi-model conversational experiences, and extensible AI tooling. I have designed OpenAI-compatible APIs for text and multimodal workloads, integrating AWS Bedrock-hosted foundation models to provide standardized LLM access across engineering teams. I have also built a TypeScript/Node.js coding agent by extending the Pi agent harness, enabling autonomous code generation, editing, and execution across multiple engineering teams. My AI engineering experience includes designing production-grade RAG systems, advanced retrieval pipelines, enterprise knowledge systems, LLM evaluation frameworks, model selection, prompt engineering, and MCP-based workflows. I have built AI assistants and meeting intelligence systems that combine RAG, metadata retrieval, and agentic workflows to automate knowledge-intensive tasks. I have also worked on high-throughput AI-driven auditing systems for large-scale GTM data analysis, focusing on automation, root-cause identification, and actionable insights. Beyond LLM applications, I have strong full-stack and backend engineering experience with Python, TypeScript, JavaScript, Node.js, Next.js, FastAPI, React, Redis, SQL/NoSQL databases, Docker, and cloud technologies. I am comfortable designing REST APIs, WebSocket-based systems, Pub/Sub architectures, caching strategies, rate limiting, microservices, and scalable distributed systems. I have also worked as a Full-Stack + AI Engineer delivering AI solutions for enterprise clients, including multimedia generation pipelines, CRM platforms, RAG integrations, and cloud storage migrations. My personal projects include a domain-specific LLM fine-tuned with LoRA for Indian land legislation and a scalable e-commerce platform built around microservices, Redis, Pub/Sub, WebSockets, caching, and high-availability principles. I enjoy solving complex engineering problems, learning emerging AI technologies, and building systems that are not only intelligent, but also maintainable, performant, secure, and production-ready.

What I'm looking for

I’m looking for AI Software Engineer roles spanning Generative AI, LLMs, AI agents, RAG, full-stack development, backend systems, infrastructure, and DevOps. I’m interested in high-ownership, technically challenging teams where I can contribute to architecture, development, cloud infrastructure, optimization, and production deployment while collaborating with strong engineering and product teams.

Experience

Senior Analyst(AI Software Engineer)

Capgemini

Oct 2025 – Present

• Engineered core capabilities of an enterprise-scale Generative AI Platform used across the organization, developing end-to-end frontend and backend features including real-time LLM response streaming, web search integration and optimisation, and extensible AI tooling to deliver a unified multi-model conversational experience. • Independently designed and built OpenAI-compatible REST API endpoints (text completions and multimodal) for a proprietary in-house GenAI platform, routing requests to AWS Bedrock-hosted foundation models, enabling standardized, secure LLM access adopted by the majority of the platform's enterprise engineering user base. • Built a TypeScript/Node.js CLI coding agent by extending the open-source Pi agent harness (pi.dev) with a custom SDK layer integrating a proprietary in-house GenAI platform, enabling multi-model LLM access for autonomous code generation, editing, and execution; adopted in production by multiple engineering teams org-wide. • Designed and built an intelligent Marketing Cloud AI Expert and Business Analyst Assistant by implementing a production-grade RAG pipeline with curated enterprise knowledge and advanced retrieval techniques; additionally developed a sandboxed LLM evaluation (Evals) framework to benchmark 15+ foundation models, optimizing model selection across AI personas and reducing inference costs by ~30% and median response latency by ~20%. • Architected a Meeting Intelligence system using Advanced RAG and metadata retrieval to extract insights from enterprise discussions; integrated MCP-based workflows for automated User story generation, delivering ~80% precision and significantly accelerating the transition from planning to execution. • Developed and managed a high-throughput AI-driven auditing system handling massive hourly workloads; automated tracking and tagging analysis for GTM while identifying root-cause issues to produce actionable SEO and performance insights for executives and technical teams. • Collaborated in Agile teams across AI, Full Stack, Cloud, and DevOps domains to deliver production-grade enterprise solutions adopted across multiple business units.

Generative AITypeScriptAWS Bedrock

Education

Certifications

Skills

Languages