Portfolio / 202601°17′S · 36°49′E

AI Engineer / Production AI systems

Elizabeth
Nyambere.

Selected systems
Focus001

I build safe, evaluated AI for domains where errors are costly.

My work covers multi-agent orchestration, RAG, and rigorous evaluation for high-stakes applications.

Email me
GitHub LinkedIn
01 / Index

Selected systems

Selected engineering work.

P—01

This Site's AI Assistant

Explore my work through a conversational assistant with inspectable references.

OpenAIRAGNext.jsQdrantEvaluation

An assistant for exploring my projects, experience, and engineering decisions. It uses an OpenAI model through Azure, retrieves curated references from Qdrant, and carries bounded conversation context. Its response contract, failure handling, and evaluation suite make the system inspectable. Citation membership is checked in code; factual support still requires evaluation.

Engineering notes

Explore the implementation and its limitations in the engineering notes. AI can make mistakes. For anything official, email me directly.

P—02

Community Health AI Assistant

Multi-agent briefings over health-record data, with evaluation and full observability.

LangGraphFastAPINext.jsRAGLLM-as-judge evalsLangfuseFHIR

An end-to-end system that gives community-health supervisors automated briefings from patient and health-worker data (OpenMRS 3 / FHIR). It uses a LangGraph agent pipeline, a FastAPI backend, and a Next.js frontend with SSE streaming. Rule-based and LLM-as-judge evaluators, a golden-question runner, and Langfuse and Grafana observability keep it accountable. I built it solo on synthetic data with Kenyan localization.

GitHub
P—03

Figma MCP Agent

An agent that turns designs of AI experiences into build plans for real AI applications.

MCPGradioClaudeAgent design

A Gradio agent that connects to Figma over the Model Context Protocol. I built it while working with a UI/UX designer, a frontend engineer, and a backend engineer. It pulls design files into context. From the designs, I decide where a product needs AI and where deterministic logic is enough, and I define each feature's output contract from what the screen displays.

A tool I built and run locally to bridge design and AI engineering. Happy to demo it on request.

Experience

02 / Index

Experience

01 / Aug 2024 – Present

AI Engineer

Prescott Data

Core contributor to Dromos, a production multi-agent AI platform. I design the agent runtime for long-running, multi-step agents, with durable state and failure recovery. I work on Odin, a graph retrieval and reasoning engine. I ship AI integrated into live systems (Microsoft Teams, EMRs, claims platforms), with evaluation and observability on every release.

02 / Mar 2024 – Aug 2024

Data Scientist

Adanian Labs

Built and deployed ML models. I built a PyTorch computer-vision model for medical-image classification and components of a credit-scoring engine. I served models with FastAPI and automated retraining pipelines.

03 / Apr 2023 – Oct 2023

Data Analyst

AMREC

Analyzed large structured and unstructured datasets with Python, R, SQL, and STATA. I built data-collection workflows and BI dashboards, and I explained statistical results to non-technical clients.

03 / Skills

Technical skills

Agent systems

01
  • +Multi-agent architecture & orchestration (LangGraph)
  • +Agent runtime design (durable state, failure recovery)
  • +MCP & tool integration
  • +Long-running, multi-step agents
  • +Prompt & context engineering
  • +Human-in-the-loop workflows

Graphs, retrieval & knowledge

02
  • +Knowledge graphs (Neo4j, ArangoDB)
  • +Graph-based retrieval & multi-hop reasoning
  • +RAG pipeline design
  • +Semantic & hybrid search
  • +Vector DBs (Pinecone, Milvus)

Evaluation & observability

03
  • +Langfuse (traces, evals, prompt A/B testing)
  • +LLM-as-judge & agent evaluation
  • +Eval loops, regression & production testing
  • +Guardrails & output contracts
  • +Grafana, Prometheus, Loki, OpenTelemetry

Models & serving

04
  • +OpenAI / Anthropic / Gemma / MedGemma
  • +AWS Bedrock, Azure OpenAI
  • +vLLM on GPU infrastructure (open-weight models)
  • +FastAPI & REST microservices

Data & infrastructure

05
  • +Python, SQL, TypeScript, React, Next.js
  • +PostgreSQL, Redis, MongoDB
  • +PyTorch & deep learning
  • +Docker, Terraform, CI/CD
  • +GCP, AWS, Azure

Principles

01

Safety and auditability

Safety means systems you can trust. I focus on explainability and auditability, so every AI decision can be traced and understood. I enforce output contracts and structured validation. The result is architecture that is transparent, secure, and ready for high-stakes environments.

02

Architecting for reliability

Production demands reliability, so I choose the right tool for each task. If a goal is measurable, I design a deterministic AI workflow. If a task is open-ended, I deploy an autonomous agent. The architecture must match the problem.

03

Human in the loop

Technology should assist people, not replace them. My systems do the heavy work and escalate ambiguous cases to people. Domain experts stay in control of the decisions that matter.

04 / Index

Profile

I connect experimental AI with dependable software.

I design, deploy, and scale AI agents. My agents combine reasoning, tool use, and access to external systems into reliable applications. I take them from prototype to production.

Open full profile

When AI makes high-stakes decisions, three layers matter most: guardrails, human oversight, and evaluation. I build these layers so every interaction is accurate, safe, and traceable. Where data control requires it, I serve open-weight LLMs on-premises with vLLM. I build the evaluation and observability layers (Langfuse, Grafana, Prometheus) that make agent behavior auditable.

I have a strong statistical foundation (BSc Biostatistics) and co-authored published research on graph intelligence. I am a Google Cloud certified Professional Machine Learning Engineer. AI changes quickly, so I study new research and lectures constantly. I explain complex technical concepts in clear terms for non-technical teams.

Research and education

05A / Research

Odin: Multi-Signal Graph Intelligence for Autonomous Discovery in Knowledge Graphs

Muyukani Kizito, Elizabeth Nyambere

A production-deployed graph-intelligence engine for autonomous pattern discovery in knowledge graphs. It introduces the COMPASS score, which combines Personalized PageRank, neural probabilistic logic, temporal decay, and GNN-based community guidance.

Read the paper
05B / Education

BSc Biostatistics

Jomo Kenyatta University of Agriculture and Technology

Second Class Upper Division Honors. A strong foundation in statistical inference and experiment design applied to health and behavioral data.

Professional Machine Learning Engineer

Google Cloud Certified

Associate Cloud Engineer

Google Cloud Certified

Beyond the work

06 / Index

Beyond the work

I am a jovial person, and I bring my whole self to the things I love. I learn new concepts fast. I think best early in the morning: a dawn focus session on a hard problem is my favorite way to start a day.

Show more

What I love most is bringing AI capabilities into applications and workflows that are already live: systems with real users and real data. I add intelligence to a system without breaking what already works. When something I built becomes part of someone's day, that keeps me going.

Away from the keyboard, I am quietly competitive: I play Scrabble to win. I train at the gym. I recharge in nature, I enjoy a good walk, and I never miss a good sunset. I read the history of ancient civilizations and contemporary African books. I keep a to-do list, and ticking off the last box is a small, honest satisfaction.

Dawn focus sessionsThe gymScrabble and friendly competitionWalks, nature, and sunsetsHistory of ancient civilizationsContemporary African booksA well-kept to-do list