For employers

Hire this AI Trainer

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

LoginCreate account
Invite to Job
T
Tuli Kumari

Tuli Kumari

AI Engineer – Data/AI Model Fine-tuning & Evaluation

India flagNew Delhi, India
$30.00/hrExpertData Annotation Tech

Key Skills

Software

Data Annotation TechData Annotation Tech

Top Subject Matter

Conversational AI
Rag Domain Expertise
Generative AI

Top Data Types

TextText
VideoVideo

Top Task Types

Fine-tuningFine-tuning

Freelancer Overview

AI Engineer – Data/AI Model Fine-tuning & Evaluation. Brings 17+ years of professional experience across complex professional workflows, research, and quality-focused execution. Core strengths include Internal and Proprietary Tooling. Education includes Master of Computer Applications, Indira Gandhi National Open University and Bachelor of Computer Applications, Indira Gandhi National Open University. AI-training focus includes data types such as Text and labeling workflows including Fine-tuning.

ExpertEnglish

Labeling Experience

AI Engineer – Data/AI Model Fine-tuning & Evaluation

TextFine Tuning
I fine-tuned and deployed Generative AI models using Ollama, vLLM, and Hugging Face for production-grade inference and deployment workloads. I designed and implemented embedding pipelines, semantic retrieval systems, and performed LLM validation and safety tasks such as hallucination detection and bias evaluation. I developed AI-powered multimedia systems and real-time ASR (Whisper, VAD, turn detection) for conversational AI, including constructing voice-enabled chatbots and automated interview platforms. • Built, validated, and optimized AI models through fine-tuning and evaluation processes • Created data labeling workflows for text, audio, and video AI pipelines • Managed LLM prompt/response dataset construction and curation for language models • Performed bias/hallucination testing, safety checks, and evaluation for model reliability

I fine-tuned and deployed Generative AI models using Ollama, vLLM, and Hugging Face for production-grade inference and deployment workloads. I designed and implemented embedding pipelines, semantic retrieval systems, and performed LLM validation and safety tasks such as hallucination detection and bias evaluation. I developed AI-powered multimedia systems and real-time ASR (Whisper, VAD, turn detection) for conversational AI, including constructing voice-enabled chatbots and automated interview platforms. • Built, validated, and optimized AI models through fine-tuning and evaluation processes • Created data labeling workflows for text, audio, and video AI pipelines • Managed LLM prompt/response dataset construction and curation for language models • Performed bias/hallucination testing, safety checks, and evaluation for model reliability

2025 - Present

Full Stack Developer – LLM Data Labeling & Fine-tuning (Contract Role)

TextFine Tuning
I designed and deployed RAG-based pipelines with context-aware response generation and built semantic search and embedding workflows for LLMs. I performed LLM fine-tuning, prompt and response writing for supervised fine-tuning (SFT), and created/modelled dataset labeling flows for text and audio. I also performed workflow optimization to ensure data quality and relevance during AI system development and deployment phases. • Executed prompt/response writing for SFT and LLM data labeling • Carried out embedding creation, annotation, and retrieval evaluation for optimal search • Developed, labeled, and fine-tuned datasets used in LLM and RAG experiments • Managed RLHF-like feedback cycles to improve AI interaction quality

I designed and deployed RAG-based pipelines with context-aware response generation and built semantic search and embedding workflows for LLMs. I performed LLM fine-tuning, prompt and response writing for supervised fine-tuning (SFT), and created/modelled dataset labeling flows for text and audio. I also performed workflow optimization to ensure data quality and relevance during AI system development and deployment phases. • Executed prompt/response writing for SFT and LLM data labeling • Carried out embedding creation, annotation, and retrieval evaluation for optimal search • Developed, labeled, and fine-tuned datasets used in LLM and RAG experiments • Managed RLHF-like feedback cycles to improve AI interaction quality

2024 - 2025

Education

I

Indira Gandhi National Open University

Bachelor of Computer Applications, Computer Applications

Bachelor of Computer Applications
Not specified
I

Indira Gandhi National Open University

Master of Computer Applications, Computer Applications

Master of Computer Applications
Not specified

Work History

P

Paladin Educators LLP

AI Engineer

New Delhi
2025 - Present
T

Turing Enterprises

Full Stack Developer

N/A
2024 - 2025