Karlo Reyes Mendoza
LLM Engineer
Cebu City, Philippines · UTC+8 · 3 years of experience
Karlo 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
RAG Trace & Groundedness Dashboard
B2B SaaS analytics platformInstrumented a customer-facing RAG assistant end to end with OpenTelemetry and Langfuse, capturing retrieval, rerank, and generation spans per request. Added groundedness and citation-coverage scoring so support and product could read quality by customer segment. Reduced the mean time to diagnose a bad answer from hours to minutes and cut unsupported claims by 34%.
Eval Harness for Structured-Output Extraction
Regional fintech lenderBuilt a regression eval suite for a loan-document extraction endpoint using OpenAI Evals and Braintrust, with 300+ labeled cases and JSON-schema validation via Pydantic and Instructor. Gated every prompt and model change behind the suite. Field extraction accuracy rose from 82% to 96% and schema-invalid responses dropped below 0.5%.
Relevant experience
Career timeline
LLM Engineer, Observability
2025–PresentSeries B B2B SaaS analytics company (remote) · Remote, Cebu City, Philippines
- Instrumented three production RAG and agent features with OpenTelemetry and Langfuse, giving the team per-request trace visibility that cut mean time to diagnose model failures from roughly 4 hours to under 20 minutes.
AI Engineer
2023–2025Customer-support automation startup · Remote, Cebu City, Philippines
- Developed RAG pipelines over a 60,000-document knowledge base using pgvector and reranking, improving answer accuracy from 71% to 89% on a curated eval set.
Software Engineering Intern to Junior Backend Developer
2022–2023Software consultancy (Cebu City) · Cebu City, Philippines
- Built and tested Python and FastAPI backend services for client web applications, contributing to 4 production releases under senior review.
Hiring this role?
See how Karlo 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
University of San Carlos · 2018–2022 · Cum Laude
Credentials
Certifications
NVIDIA-Certified Associate: Generative AI LLMs
NVIDIA · 2025 · Certified
AWS Certified Machine Learning Engineer – Associate
Amazon Web Services · 2024 · Certified
Communication
Languages
Filipino (Tagalog)
Native
Cebuano
Native
English
Fluent
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.
Henrique Vasconcelos
Senior LLM Engineer
Senior LLM engineer, 9 years, specializing in structured outputs and tool calling.