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

Applied AI Engineer and Python specialist with 4+ years of software engineering experience delivering production-grade AI/LLM systems, RAG pipelines, and agentic workflows. Builds end-to-end, low-latency semantic retrieval systems and responsible AI guardrails focused on reliability, traceability, and security across the full lifecycle. Experienced in FastAPI, OpenAI/Claude APIs, pgvector-based retrieval, and cloud infrastructure on AWS/GCP/Azure. Proven ability to lead multiple concurrent client projects, mentor engineers, and improve reliability and performance through structured engineering practices, CI/CD, and production monitoring.…Applied AI Engineer and Python specialist with 4+ years of software engineering experience delivering production-grade AI/LLM systems, RAG pipelines, and agentic workflows. Builds end-to-end, low-latency semantic retrieval systems and responsible AI guardrails focused on reliability, traceability, and security across the full lifecycle. Experienced in FastAPI, OpenAI/Claude APIs, pgvector-based retrieval, and cloud infrastructure on AWS/GCP/Azure. Proven ability to lead multiple concurrent client projects, mentor engineers, and improve reliability and performance through structured engineering practices, CI/CD, and production monitoring.

Lloyd Aloysius

AI Engineer, Back-End Developer, Software Engineer, +1





Applied AI Engineer and Python specialist with 4+ years of software engineering experience delivering production-grade AI/LLM systems, RAG pipelines, and agentic workflows. Builds end-to-end, low-latency semantic retrieval systems and responsible AI guardrails focused on reliability, traceability, and security across the full lifecycle. Experienced in FastAPI, OpenAI/Claude APIs, pgvector-based retrieval, and cloud infrastructure on AWS/GCP/Azure. Proven ability to lead multiple concurrent client projects, mentor engineers, and improve reliability and performance through structured engineering practices, CI/CD, and production monitoring.…Applied AI Engineer and Python specialist with 4+ years of software engineering experience delivering production-grade AI/LLM systems, RAG pipelines, and agentic workflows. Builds end-to-end, low-latency semantic retrieval systems and responsible AI guardrails focused on reliability, traceability, and security across the full lifecycle. Experienced in FastAPI, OpenAI/Claude APIs, pgvector-based retrieval, and cloud infrastructure on AWS/GCP/Azure. Proven ability to lead multiple concurrent client projects, mentor engineers, and improve reliability and performance through structured engineering practices, CI/CD, and production monitoring.

Available to hire

Applied AI Engineer and Python specialist with 4+ years of software engineering experience delivering production-grade AI/LLM systems, RAG pipelines, and agentic workflows. Builds end-to-end, low-latency semantic retrieval systems and responsible AI guardrails focused on reliability, traceability, and security across the full lifecycle.

Experienced in FastAPI, OpenAI/Claude APIs, pgvector-based retrieval, and cloud infrastructure on AWS/GCP/Azure. Proven ability to lead multiple concurrent client projects, mentor engineers, and improve reliability and performance through structured engineering practices, CI/CD, and production monitoring.

Skills

Experience Level

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Intermediate

Intermediate

Intermediate

Intermediate

Intermediate

Intermediate

Intermediate

Intermediate

Language

English

Advanced

Work Experience

Applied AI & LLM Engineer at Britic a n a

December 1, 2025 - May 1, 2026

Designed and deployed end-to-end RAG pipelines using pgvector, OpenAI API, and Claude API to support large document corpora with low-latency semantic retrieval. Engineered multi-step agentic workflows using MCP orchestration and non-cloud-hosted infrastructure, reducing manual research effort across recurring tasks. Built and maintained FastAPI backend services with structured logging, Pydantic validation, and per-request traceability to maintain reliable uptime across LLM-integrated pipelines. Implemented responsible AI guardrails, data privacy controls, and bias evaluation across LLM systems from architecture through deployment. (Dates shown in resume as Dec 2025 – May 2026.)

AI Research Workflow Orchestrator (Project)

August 1, 2025 - Present

Built a multi-step agentic pipeline using n8n, MCP server integrations, LLM reasoning, and vector embeddings on self-hosted infrastructure. Designed and iterated multi-agent coordination patterns based on real-world usage, improving pipeline reliability and output consistency.

Proxmox Manager Stream Deck Plugin (Project)

January 1, 2025 - Present

Developed a REST API integration against Proxmox VE with token authentication, polling architecture, request deduplication, and real-time state management across distributed nodes. Delivered via a 6-phase CI/CD workflow with automated build, release, and quality assurance at every stage.

Agent-Based Epidemic Simulation (MSc Research)

June 1, 2024 - Present

Modeled multi-agent behaviour across 10,000+ agent simulation runs with parameterised scenario analysis and statistical policy evaluation.

Deck AI — Document Intelligence & RAG System (Project)

January 1, 2024 - Present

Built an end-to-end RAG pipeline using pgvector, Claude API, and 300-token chunking with SHA-256 embedding cache for semantic document retrieval. Architected full-stack solution (Next.js, FastAPI, PostgreSQL + pgvector) with formal SRS documentation, structured logging, and per-request traceability. Implemented AI guardrails and data privacy controls across all pipeline stages to ensure responsible and secure LLM usage.

Project Lead / Software Developer (AI/Backend focus)

January 1, 2019 - January 1, 2022

Led technical delivery on 5+ concurrent client projects, providing technical scoping, database schema design, and code architecture across teams of 3–5 engineers. Designed and maintained RESTful microservices integrated with React frontends; led a service migration that reduced downtime by 50% and improved deployment independence across services. Optimized MySQL schemas and query execution plans for data-heavy production workloads, improving average API response times by 30% across stable datasets (10M+ records). Built Docker-based CI/CD pipelines with structured logging and production monitoring, reducing mean time to incident resolution (MTTR) by 35%. Mentored 3+ junior engineers through code review and pair programming, establishing shared coding standards that reduced production bugs by 25% over 6 months.