Cris N.

Key Skills

Software

Don't disclose

Top Subject Matter

LLM systems for motorsport telemetry and multilingual conversational assistants (RAG, multi-agent orchestration).

Top Data Types

Text

Top Task Types

Tracking

Freelancer Overview

Independent AI Application Engineer & Founder - Self-employed. Brings 18+ years of professional experience across complex professional workflows, research, and quality-focused execution. Core strengths include Don't disclose. Education includes Bachelor of Science, Universidade La Salle and N/A, Uninter. AI-training focus includes data types such as Computer Code, Programming, and Text and labeling workflows including Evaluation, Rating, and Tracking.

Labeling Experience

Independent AI Application Engineer & Founder - Self-employed

TextTracking

Built end-to-end production LLM solutions focused on prompt engineering, RAG, and multi-agent orchestration for motorsport telemetry. Designed and implemented conversational AI with tiered model routing and persistent per-user memory while maintaining answer quality through rigorous evaluation and cross-checking. Developed supporting full-stack capabilities in Python and FastAPI, integrating external services for marketplace payments and server-side business logic. • Layered LLM architecture with on-demand RAG • Multi-agent Python/FastAPI orchestration and prompt iteration • Output evaluation and reliability checks across AI systems • Mercado Pago/Stripe integrations with recomputation of prices and commissions

2023 - Present

Independent AI Application Engineer & Founder (2023–Present) — LLM systems development with evaluation of model outputs for correctness and quality.

Don't disclose

Built and iterated an LLM assistant architecture that ingests real-time telemetry and normalizes data across multiple ECU brands using retrieval-augmented generation (RAG) outputs. Performed daily evaluation and cross-checking of AI responses for correctness, factual accuracy, and overall quality to ensure reliability across multiple AI systems. Delivered multilingual, user-memory-enabled conversational assistance with tiered model routing and a specialized RAG knowledge base for consistent answer generation. • Prompt design and iterative refinement for system behavior • Output evaluation for correctness and factual accuracy • Cross-checking across multiple AI systems for reliability • Translation-ready, multilingual answer delivery (PT/ES/EN)

2023 - Present

Education

Work History