Henrique Vasconcelos
Senior LLM Engineer
Florianopolis, Brazil · UTC-3 (America/Sao_Paulo) · 9 years of experience
Henrique focuses on measurable model behavior, reliable retrieval, and production evaluation.
Request a shortlistWhy this profile fits
Evaluation before optimization
Defines datasets, graders, and regression checks so model changes are measured against real failure cases.
Reliable retrieval and tool use
Improves grounding, structured outputs, tool permissions, and recovery behavior for production workflows.
Cost and latency control
Treats task success, response time, and model spend as one production system rather than separate concerns.
Relevant toolkit
Python
LangGraph
Claude API
OpenAI GPT API
PostgreSQLDelivery evidence
Selected work
Schema-Locked Extraction Engine
Enterprise insurance SaaSDesigned a tool-calling extraction service that parses unstructured policy and claims documents into strict JSON schemas validated on every response. Added a repair loop and confidence scoring so invalid outputs self-correct or route to review. Cut manual data entry by 70% and reached 99.5% schema validity across 2 million documents a year.
Agentic Operations Copilot
Logistics scale-upBuilt a LangGraph agent that calls internal APIs through typed function definitions to answer operational questions and trigger actions like rescheduling shipments. Added tool-call evals and guardrails to block unsafe writes before they reached production. Reduced average resolution time for ops tickets from 14 minutes to under 4.
Relevant experience
Career timeline
Senior LLM Engineer
Jan 2024–PresentEnterprise SaaS (AI document automation) · Remote, Brazil (UTC-3)
- Owned the structured-outputs and tool-calling layer for a document automation product, lifting JSON schema validity from 88% to 99.6% across more than 2 million documents processed annually.
LLM / NLP Engineer
Mar 2021–Dec 2023B2B SaaS (developer tools) · Remote
- Built a retrieval augmented assistant over technical docs with hybrid search and reranking, deflecting 32% of inbound support tickets within one quarter.
Machine Learning Engineer
Jun 2019–Feb 2021Fintech scale-up · Sao Paulo, Brazil
- Developed NLP models for transaction categorization and document OCR post-processing, raising categorization accuracy from 84% to 93% on more than 5 million monthly events.
Hiring this role?
See how Henrique fits the LLM Engineer role.
Skill depth
Show experience in context.
Relevant experience by skill
See the complete skill index
Languages
Frameworks
Libraries/APIs
Tools
Paradigms
Platforms
Storage
Other
Education
Formal background
Bachelor of Science, Computer Science
Universidade Federal de Santa Catarina · 2013–2017 · Graduated with honors
Lato Sensu Postgraduate Certificate, Machine Learning and Artificial Intelligence
Pontificia Universidade Catolica de Minas Gerais · 2019–2020
Credentials
Certifications
AWS Certified Machine Learning Engineer – Associate
Amazon Web Services · 2025 · Certified
AWS Certified Generative AI Developer – Professional
Amazon Web Services · 2026 · Certified
Communication
Languages
Portuguese
Native
English
Fluent
Spanish
Professional
More examples
Similar LLM Engineer profiles.
Aravind Balakrishnan
Senior LLM Engineer
Senior LLM engineer, 13 years, specializing in RAG retrieval quality and eval-driven model behavior.
Kacper Wiśniewski
Senior LLM Engineer
Senior LLM engineer who makes model behavior measurable, not anecdotal.
Tomás Ferreyra
Senior LLM Engineer
Senior LLM engineer specializing in model routing and cost control.