For employers

Hire this AI Trainer

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

LoginCreate account
Invite to Job
M
Miguel Nhassengo

Miguel Nhassengo

Senior AI Training Specialist (RLHF & Human Feedback Labeling)

Mozambique flagMaputo Province, Mozambique
$2.20/hrIntermediate

Key Skills

Software

No software listed

Top Subject Matter

Large Language Models
Human Preference Alignment
LLM Security Evaluation

Top Data Types

TextText
ImageImage

Top Task Types

RLHFRLHF
Red TeamingRed Teaming
Fine-tuningFine-tuning
Data CollectionData Collection

Freelancer Overview

Senior AI Training Specialist (RLHF & Human Feedback Labeling). Brings 10+ years of professional experience across complex professional workflows, research, and quality-focused execution. Core strengths include Internal and Proprietary Tooling. Education includes Bachelor of Science, N/A (2017). AI-training focus includes data types such as Text and labeling workflows including RLHF, Red Teaming, and Fine-tuning.

IntermediateEnglish

Labeling Experience

Senior AI Training Specialist (Red Teaming & Evaluation)

TextRed Teaming
I developed and led adversarial evaluation efforts to test LLM vulnerabilities using Red Teaming protocols. This involved designing and administering adversarial prompts to identify failures and risky behaviors. Results from these tests directly contributed to the creation of security patches and mitigation strategies. • Coordinated manual and automated adversarial prompt creation. • Managed data collection efforts for dangerous or undesirable model outputs. • Implemented documentation protocols to track discovered vulnerabilities. • Provided feedback to engineering teams to improve LLM safety and robustness.

I developed and led adversarial evaluation efforts to test LLM vulnerabilities using Red Teaming protocols. This involved designing and administering adversarial prompts to identify failures and risky behaviors. Results from these tests directly contributed to the creation of security patches and mitigation strategies. • Coordinated manual and automated adversarial prompt creation. • Managed data collection efforts for dangerous or undesirable model outputs. • Implemented documentation protocols to track discovered vulnerabilities. • Provided feedback to engineering teams to improve LLM safety and robustness.

2022 - Present

Senior AI Training Specialist (RLHF & Human Feedback Labeling)

TextRLHF
As Senior AI Training Specialist, I led AI training projects focused on aligning large language models with human preferences. I designed and implemented RLHF pipelines incorporating large-scale human feedback. These efforts resulted in measurable improvements in model reasoning and reductions in hallucination rates. • Implemented reward modeling strategies utilizing human preference data. • Supervised a team handling preferences labeling and multi-step feedback loops. • Established quality control benchmarks to ensure signal reliability. • Collaborated with engineers to automate and scale data labeling operations.

As Senior AI Training Specialist, I led AI training projects focused on aligning large language models with human preferences. I designed and implemented RLHF pipelines incorporating large-scale human feedback. These efforts resulted in measurable improvements in model reasoning and reductions in hallucination rates. • Implemented reward modeling strategies utilizing human preference data. • Supervised a team handling preferences labeling and multi-step feedback loops. • Established quality control benchmarks to ensure signal reliability. • Collaborated with engineers to automate and scale data labeling operations.

2022 - Present

AI Research Engineer (SFT & Data Curation)

TextFine Tuning
As an AI Research Engineer, I participated in supervised fine-tuning of neural models for custom tasks. This included curating and preprocessing datasets and adjusting model outputs to improve relevance and consistency. My work contributed to increased accuracy and targeted domain adaptation of NLP systems. • Collaborated with UX teams to annotate and review AI responses for personality alignment. • Oversaw creation of domain-specific labeling guidelines. • Coordinated data preprocessing and augmentation pipelines for training runs. • Ensured annotated data consistency across large-scale multi-modal projects.

As an AI Research Engineer, I participated in supervised fine-tuning of neural models for custom tasks. This included curating and preprocessing datasets and adjusting model outputs to improve relevance and consistency. My work contributed to increased accuracy and targeted domain adaptation of NLP systems. • Collaborated with UX teams to annotate and review AI responses for personality alignment. • Oversaw creation of domain-specific labeling guidelines. • Coordinated data preprocessing and augmentation pipelines for training runs. • Ensured annotated data consistency across large-scale multi-modal projects.

2019 - 2021

Machine Learning Developer (Data Preparation for Labeling)

TextData Collection
As a Machine Learning Developer (Junior), I handled cleaning and preparing data for supervised learning, ensuring accuracy and reliability. I developed automation tools specifically to streamline data readiness for downstream labeling and training. This role was foundational for efficient and noise-reduced model training. • Cleaned, filtered, and normalized raw textual datasets. • Developed Python scripts to automate and systematize data preparation. • Conducted manual reviews to assess annotation quality. • Maintained documentation to ensure reproducibility for the labeling process.

As a Machine Learning Developer (Junior), I handled cleaning and preparing data for supervised learning, ensuring accuracy and reliability. I developed automation tools specifically to streamline data readiness for downstream labeling and training. This role was foundational for efficient and noise-reduced model training. • Cleaned, filtered, and normalized raw textual datasets. • Developed Python scripts to automate and systematize data preparation. • Conducted manual reviews to assess annotation quality. • Maintained documentation to ensure reproducibility for the labeling process.

2017 - 2019

Education

N

N/A

Bachelor of Science, Computer Science and Engineering

Bachelor of Science
2013 - 2017

Work History

N

NeuralCore Systems

Senior AI Training Specialist

San Francisco
2022 - Present
S

Synthesis Labs

AI Research Engineer

San Francisco
2019 - 2021