Itix
Itix
51 – 200 Employees
ConsultingHealthcareLogistics
Itix is a Brazilian technology and consulting company that helps organizations modernize operations through custom software platforms, dedicated development teams, and technology consulting. Its services also include support and analytics or business intelligence, enabling enterprise customers to improve processes and use data more effectively. Itix works with organizations in areas including industry, finance, healthcare, logistics, insurance, energy, chemical, and mining, supported by distributed teams across Brazil.

Data Scientist, Generative AI — Remote at Itix

Build cognitive engines, retrieval-augmented generation systems, and multimodal document analysis for Itix’s software factory. Evaluate large language models and extract structured data from documents.

Description

  • Design the cognitive engine architecture from API input payload through output JSON
  • Develop specialized prompts using chain-of-thought reasoning, anti-hallucination safeguards, and JSON Schema
  • Implement Gemini-based multimodal analysis, including document OCR, computer vision, structured field extraction, and inconsistency detection
  • Build RAG pipelines with semantic chunking, coverage, clause, and limit metadata, embeddings, hybrid search, and reranking
  • Calibrate models with historical cases and few-shot learning, including edge cases
  • Develop an evaluation framework with automated test suites, accuracy, precision, recall, and regression benchmarks
  • Track inference quality, cost, and latency while implementing LLM observability and prompt versioning
  • Validate outputs in collaboration with business analysts

Requirements

  • Advanced Python skills and experience building REST APIs with FastAPI or a comparable framework
  • Production experience with large language models, including prompt engineering, structured JSON Schema output, function calling, and anti-hallucination methods
  • Demonstrated RAG experience with embeddings, vector databases such as pgvector, Vertex AI Vector Search, Pinecone, or Qdrant, plus chunking, reranking, and retrieval evaluation
  • Experience using multimodal models, preferably Gemini, with OCR and computer vision for documents and images
  • Knowledge of LLM evaluation practices, including golden datasets, accuracy, precision, recall, and regression testing
  • Familiarity with Databricks, including notebooks, MLflow, and Delta Lake, and AWS for collaboration with data engineering
  • Proficiency with Git, coding best practices, and automated testing
  • Preferred: Google Cloud or Vertex AI and Gemini API; LangChain, LlamaIndex, or LangGraph; Ragas, DeepEval, or LangSmith; insurance, claims, claims adjustment, legal, or contractual documents; MLflow; Brazil’s LGPD and data anonymization; LLM guardrails and red teaming; Databricks, Google Cloud, or AI certifications

Benefits

  • Work remotely with geographic flexibility to choose the location that works best for you
  • Access partner coupons and referral offers for car rentals, language schools, undergraduate and graduate programs, and more
  • Earn rewards through the talent referral program
  • Take your birthday off
  • Use TotalPass/Wellhub
  • Access integrated physical and mental healthcare through a telemedicine platform
  • Participate in health and quality-of-life programs
  • Use office relaxation spaces with bean bags, a pool table, video games, a break room, a fully equipped kitchen, and coffee

Related Jobs

Kreato Global | BPO and Language Solutions

Remote English-Spanish OPI/VRI Interpreter

Kreato Global | BPO and Language Solutions
201 – 500 Employees
HealthcareHospitalityLogistics

Interpret remotely between English- and Spanish-speaking people in medical, financial, social service, and customer care settings. Provide language support for Kreato Global across Latin America.

Open