Are you driven by technology, data, and innovation? At Triggo.ai, we transform complex challenges into intelligent solutions. We are a Brazilian company focused on Analytics, AI, and digital transformation, helping organizations make more strategic decisions and generate real business impact. We work across various market sectors, always combining cutting-edge technology, business insight, and agile execution. If you want to build solutions that make a difference and grow alongside a high-performance team, this could be your place. Join Triggo.ai and build the future with us. **Responsibilities and Duties** * Design end-to-end NLP pipelines: entity extraction, terminological normalization, semantic matching, and clustering; * Conduct exploratory phases (EDA, data quality assessment, completeness, analytical feasibility) on structured and unstructured datasets; * Define modeling approaches between fine-tuning Transformer models (BERTimbau and similar) and using LLMs for extraction/structuring, with clear criteria for reproducibility, cost, and auditability; * Build embedding, RAG, and semantic search pipelines with vector databases (Qdrant, Milvus, ChromaDB); * Calibrate prioritization and anomaly detection scores (Isolation Forest, Autoencoders, HDBSCAN) in collaboration with domain experts; * Version experiments and models to ensure traceability and governance; * Produce high-level technical and scientific documentation (reports and, where applicable, publications); * Serve as the technical liaison with domain experts for validation of criteria, thresholds, and metrics. **Requirements and Qualifications** * Degree in Data Science, Statistics, Computer Science, or related fields; * 5+ years of experience delivering NLP projects in production, preferably in Portuguese; * Strong proficiency in Python, pandas, scikit-learn, and PyTorch (Transformers); * Practical experience with Transformer models (BERTimbau, multilingual BERT); * Applied Generative AI: prompt engineering, RAG, structured outputs, embeddings, and tool use; * Hugging Face Transformers, spaCy, and sentence-transformers; * Vector databases (Qdrant, Milvus, or ChromaDB) and similarity search; * Proficiency in CRISP-DM methodology and MLOps fundamentals (MLflow); * Ability to communicate technical results to both technical and non-technical audiences; * Experience serving open-source LLMs (vLLM, Ollama, TGI, llama.cpp) in on-premise GPU environments; * Knowledge of GPU orchestration in Kubernetes (GPU pass-through, MIG, NVIDIA GPU Operator); * Scientific publications in NLP, ML, or applied data science; * Experience with low-standardization free-text corpora and typical natural language data quality challenges. We are the **SysMap Group**, comprising the brands **SysMap Solutions, TriggoLabs, and triggo.ai**, an ecosystem of high-impact companies in the market, delivering innovative technology solutions that transform businesses and develop people. Our essence is driven by **a passion for innovation, collaboration, and continuous growth**. For over **25 years**, we have exceeded expectations by solving complex business challenges, operating across diverse sectors and actively tracking technological evolution. Here, we believe that **technology only delivers value when built by people**. Therefore, we cultivate an ethical, collaborative, and diverse environment where learning is constant and excellence in what we do is part of our identity. **The only way to participate in SysMap Group selection processes is through the company pages on the Gupy platform; no participation or hiring fees apply.**
João Silva
Indeed · HR
João Silva
Indeed · HR
