For employers

Hire this AI Trainer

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

Invite to Job
Sakshi Tiwari

Sakshi Tiwari

AI Engineer - Generative AI & Agentic Systems

INDIA flag
Lucknow, India
$18.00/hrEntry LevelOther

Key Skills

Software

Other

Top Subject Matter

No subject matter listed

Top Data Types

TextText

Top Label Types

Classification
Evaluation Rating

Freelancer Overview

I am a B.Tech graduate with hands-on experience in building and deploying AI systems, specializing in NLP, prompt engineering, and data-centric workflows. My work includes fine-tuning large language models (using LoRA/QLoRA), designing RAG pipelines, and developing robust evaluation methods such as LLM-as-a-judge and entity-level precision checks to ensure high-quality, reliable AI outputs. I have implemented data annotation and validation processes in production-ready applications for HealthTech and FinTech, with a strong focus on reducing hallucinations and improving data relevance. My technical toolkit includes Python, PyTorch, Hugging Face, LangChain, FAISS, and FastAPI, and I have a proven track record of integrating and evaluating AI models using real-world datasets to drive measurable improvements in accuracy and user satisfaction.

Entry LevelEnglish

Labeling Experience

RAG PIPELINES

OtherTextClassificationEvaluation Rating
Developed and evaluated a 7-agent LangGraph-based AI system for real-time financial news intelligence. Processed and deduplicated 500+ articles per day with 97% accuracy using semantic similarity + metadata matching. Implemented and optimized RAG pipelines (using FAISS, semantic chunking, hybrid search) to ground LLM responses in live news data. Performed extensive model evaluation including: - Hallucination reduction (32% improvement vs baseline) - Entity-level precision and recall metrics - LLM-as-a-Judge scoring to compare agent behaviors and output quality - User satisfaction evaluation (92% on generated Python trading strategies) Deployed production-grade system with JWT authentication, encryption, and audit logging using FastAPI and Docker.

Developed and evaluated a 7-agent LangGraph-based AI system for real-time financial news intelligence. Processed and deduplicated 500+ articles per day with 97% accuracy using semantic similarity + metadata matching. Implemented and optimized RAG pipelines (using FAISS, semantic chunking, hybrid search) to ground LLM responses in live news data. Performed extensive model evaluation including: - Hallucination reduction (32% improvement vs baseline) - Entity-level precision and recall metrics - LLM-as-a-Judge scoring to compare agent behaviors and output quality - User satisfaction evaluation (92% on generated Python trading strategies) Deployed production-grade system with JWT authentication, encryption, and audit logging using FastAPI and Docker.

2025 - 2025

Education

B

BN COLLEGE OF ENGINEERING AND TECHNOLOGY

BTECH, ECE

BTECH
2021 - 2025
B

BN College of Engineering and Technology

Bachelor of Technology, Electronics and Communication Engineering

Bachelor of Technology
2021 - 2025

Work History

G

Gracker.ai

Full Stack AI Intern

Remote
2025 - 2025
A

Apana Time Tech Solutions

AI Engineer Intern

Remote
2025 - 2025