Open to opportunities

Panitra Pandey

@panitrapandey

Message

AI/ML Engineer building LLM moderation, multi-agent trust systems, and production-ready scalable inference pipelines.

India

Message

What I'm looking for

I’m looking for a team building production-grade AI with strong trust & safety, guardrails, and real-time reliability. I want to own end-to-end ML—from model evaluation to FastAPI/CI/CD deployment—while shipping measurable improvements.

I’m an AI/ML engineer focused on deploying reliable, production-oriented AI systems—especially LLM-based moderation, trust and safety workflows, and real-time detection. I build with guardrails and deterministic outputs to reduce operational risk while improving user outcomes.

Most recently, I built SayzoGuard, a multi-layered detection system preventing contact leakage, fraud, and policy violations in real-time communication. I developed LLM-based moderation pipelines with guardrails, designed multi-agent architectures for trust and safety workflows, and engineered scalable backend services with real-time inference using FastAPI.

Earlier, I delivered an AI-powered coding assistant using NLP for real-time code suggestions and error detection, plus LLM-driven task distribution to optimize workload allocation and team efficiency. I’ve also automated document workflows with NLP/ML (including an SOW automation project that reduced creation time by 50%) and supported model deployment using CI/CD pipelines and containerized environments across AWS, GCP, and Docker.

Experience

Work history, roles, and key accomplishments

Current

AI Research Engineer

Current

Sayzo

Oct 2025 - Present (7 months)

Built SayzoGuard, a multi-layered real-time detection system to prevent contact leakage, fraud, and policy violations in marketplace communications. Developed LLM-based moderation pipelines with guardrails and multi-agent trust/safety workflows to improve modularity, traceability, and reduce false negatives.

LLM Moderation Guardrails For Deterministic Outputs fastAPI NLP

AI Engineer (R&D)

AI Horse

Apr 2024 - Apr 2025 (1 year)

Built an AI-powered coding assistant using NLP for real-time code suggestions and error detection. Developed LLM-based task distribution and fine-tuned an employee recommendation system, then deployed models via CI/CD with containerized workflows and standard evaluation metrics.

NLP LLM TensorFlow PyTorch Code Intelligence Model Evaluation (Precision Recall F1 ROC AUC)CI CD For ML Hyperparameter Tuning

AI Engineer (R&D)

Eudemonics Technologies

Aug 2023 - Dec 2023 (4 months)

Led development of an AI system automating SOW document detection/creation using NLP and ML, including feedback loops to improve accuracy and adaptability. Reduced SOW creation time by 50% by delivering the solution end-to-end from data preparation through deployment.

NLP Document Understanding Model Training data preprocessing Deployment