For employers

Hire this AI Trainer

Sign in or create an account to invite AI Trainers to your job.

LoginCreate account
Invite to Job
L
Lamec Orengo

Lamec Orengo

LLM Evaluation Pipeline and RLHF Exposure (Intern, Google DeepMind)

USA flagAtlanta, Usa
ExpertOther

Key Skills

Software

Other

Top Subject Matter

Large Language Models (LLMs)
Rlhf Domain Expertise
Model Alignment and Safety

Top Data Types

TextText

Top Task Types

Fine-tuningFine-tuning

Freelancer Overview

LLM Evaluation Pipeline and RLHF Exposure (Intern, Google DeepMind). Brings 6+ years of professional experience across complex professional workflows, research, and quality-focused execution. Core strengths include Internal, Proprietary Tooling, and Other. Education includes Master of Science, Carnegie Mellon University (2021) and Bachelor of Science, Stanford University (2020). AI-training focus includes data types such as Text and labeling workflows including Evaluation, Rating, and Fine-tuning.

Expert

Labeling Experience

LLM Fine-Tuning Pipeline (Freelance AI Specialist)

OtherTextFine Tuning
Designed and implemented end-to-end pipelines for fine-tuning open-source large language models on domain-specific datasets. Utilized LoRA/QLoRA to tailor model outputs for specialized applications with robust evaluation steps. Managed data preprocessing, cleaning, and supervised fine-tuning tasks to ensure effective learning from curated datasets. • Developed fine-tuning pipelines using HuggingFace and Python • Performed supervised learning and quality assessment of model outputs • Managed and annotated domain-specific data for training • Integrated and evaluated fine-tuned models within product workflows

Designed and implemented end-to-end pipelines for fine-tuning open-source large language models on domain-specific datasets. Utilized LoRA/QLoRA to tailor model outputs for specialized applications with robust evaluation steps. Managed data preprocessing, cleaning, and supervised fine-tuning tasks to ensure effective learning from curated datasets. • Developed fine-tuning pipelines using HuggingFace and Python • Performed supervised learning and quality assessment of model outputs • Managed and annotated domain-specific data for training • Integrated and evaluated fine-tuned models within product workflows

2023 - Present

LLM Evaluation Pipeline and RLHF Exposure (Intern, Google DeepMind)

Text
Worked on building internal LLM benchmarking and evaluation tooling to assess large language models' performance. Developed and implemented data pipelines for model evaluation, contributing to improved throughput and assessment quality. Directly exposed to RLHF, alignment, and safety evaluation workflows within a research setting. • Designed Python-based evaluation harnesses for large language models • Benchmarked LLM outputs and assessed quality of responses • Integrated feedback and rating processes into model testing pipelines • Supported research reviews of LLM alignment and human feedback methods

Worked on building internal LLM benchmarking and evaluation tooling to assess large language models' performance. Developed and implemented data pipelines for model evaluation, contributing to improved throughput and assessment quality. Directly exposed to RLHF, alignment, and safety evaluation workflows within a research setting. • Designed Python-based evaluation harnesses for large language models • Benchmarked LLM outputs and assessed quality of responses • Integrated feedback and rating processes into model testing pipelines • Supported research reviews of LLM alignment and human feedback methods

2023 - 2023

Education

C

Carnegie Mellon University

Master of Science, Computational Mathematics

Master of Science
2020 - 2021
M

MIT Sloan, MIT

Bachelor of Science, Business and Commerce

Bachelor of Science
2016 - 2020

Work History

S

Self-Employed

Freelance Web Developer & AI Specialist

Atlanta
2023 - Present
G

Google

AI/ML Software Engineer Intern

Mountain View
2023 - 2023