Wigiwork — Remote Tech, AI & Fintech Talent MarketplaceWigiwork — Remote Tech, AI & Fintech Talent Marketplace
Log inSign up
cassiandebugger's avatar
@cassiandebugger

AI Engineer | Agentic LLM Systems, RAG & Evaluation

$4,900/mo

Madrid

Experience: 5 yearsOpen to: Madrid·

Wigi highlights

5+ years, currently working as Senior AI Engineer

Built and shipped a custom Python dialog-agent framework

Shipped a hybrid RAG system in production using Qdrant

Works in data and AI. Built an LLM evaluation framework with synthetic golden-set generation, LLM-as-judge scoring with position-bias randomization and manual judge validation, and benchmarked it against an OpenAI Assistants API baseline (file_search + vector stores) at 97% vs 94% accuracy on internal data. Works on RAG retrieval with hybrid search and LLM reranking, automated data labeling, normalization and chunking, and LLM integration at the retrieval and generation stages. Builds and runs agentic LLM systems in production, including orchestration, context engineering, hybrid RAG, step-level observability and evaluation that proves they actually work. Among the listed skills are ClickHouse, Embeddings, Function Calling, Generative AI and GPT.

Open to offers

Open to new opportunities

Skills
Tech stack
ClickHouseClickHouse
Tools & workflows
Large Language Models (LLM)
Large Language Model (LLM) Agents
AI Agents
Generative AI
Retrieval-Augmented Generation (RAG)
Large Language Model (LLM) Evaluation
LLM-as-Judge
OpenAI API
Anthropic Claude
Claude Code
Function Calling
MCP
Prompt Engineering
GPT
Agentic AI
Embeddings
Vector Representations
Vector Search
Vector Databases
Work experience
· 3 roles

AI Evaluation Engineer

Company hidden · under 1 year

AI Systems Developer

Company hidden · 1-3 years

Data Scientist - NLP & ML

Company hidden · 1-3 years

More on this profile

Unlocks when they connect with you.

  • education· 2

Similar available AI Engineers

View all