Looking for a job

Daniel Boadzie

@danielboadzie

Message

I build reliable agentic, RAG, and LLM platforms for regulated production environments.

Ghana

Message

What I'm looking for

I'm looking to build reliable agentic and RAG systems where grounding, evaluation, auditability, and safe deployment matter—especially in regulated or high-trust environments.

I've built and operated production LLM systems across payments, energy infrastructure, and regulated legal retrieval. At Hubtel, I deployed ML and LLM applications for a payments platform serving 2M+ users, cutting inference latency by 60% and building evaluation pipelines to catch regressions before production.

At Kofa, I shipped LangChain and LangGraph agentic workflows for data processing, analysis, and reporting. I also built RAG systems over proprietary operational data, reducing hallucinations by 40% through grounding and citation enforcement while maintaining 99.8% uptime on AWS.

As Founder and Principal Engineer at Quitos AI, I architect and run an end-to-end LLM platform with model routing, caching, batching, telemetry, incident response, and guardrails. I also build MCP and self-hosted RAG systems designed for trustworthy AI, auditability, and sensitive-data protection.

Experience

Work history, roles, and key accomplishments

Current

Founder & Principal Engineer

Current

Quitos AI

Jan 2026 - Present (8 months)

Architect and operate a production LLM platform end-to-end, including provider integration, prompt and context management, request routing, and graceful degradation. Optimize for performance, reliability, latency, and cost through model routing, caching, and batching.

LLM Platforms Model Routing Caching Batch Processing Telemetry Alerting Incident Response GuardRails Abuse prevention

AI / Data Engineer

Kofa

Apr 2025 - Dec 2025 (8 months)

Designed and shipped agentic workflows using LangChain and LangGraph, automating data processing, analysis, and reporting. Built RAG systems over proprietary operational data, reducing hallucinations by 40% through grounding and citation enforcement.

Lang Chain LangGraph RAG Vector Databases Reranking Retrieval Evaluation AWS Docker CI CD Monitoring Evaluation Frameworks

Machine Learning Specialist

Hubtel

Aug 2023 - Mar 2025 (1 year 7 months)

Built and deployed ML and LLM applications on a regulated payments platform serving 2M+ users, integrating OpenAI and Anthropic APIs. Delivered fraud detection at scale, cutting inference latency by 60% and building evaluation pipelines to catch regressions pre-production.

Machine Learning LLM OpenAI Anthropic Fraud Detection Data Governance Access Control Auditability Evaluation Pipelines

CTO / Data Science Lead

Zummit Africa

Jan 2022 - Dec 2022 (11 months)

Set architecture and engineering standards, partnered with business stakeholders to scope AI automation opportunities, and delivered them to production.

Architecture Engineering standards AI Automation Stakeholder Management Production Deployment