Open to opportunities

Anchal Pathak

@anchalpathak

Message

AI Engineer building production-grade generative AI systems and agentic multimodal workflows.

India

Message

What I'm looking for

I’m looking for a role where I can ship production-grade agentic generative AI and multimodal systems, build FastAPI services, and continuously improve quality through prompt/model evaluation for accuracy and reliability.

I’m an AI Engineer with 2+ years building production-grade generative AI systems—from multimodal storyboard pipelines to real-time computer vision. I’ve shipped LLM-powered features at scale using Claude, Gemini, and OpenAI APIs, while also contributing peer-reviewed AI research with 98.71% accuracy on the KFall dataset.

In my recent work, I architect end-to-end agentic workflows for automated ad creation, develop multimodal creative automation platforms, and deploy FastAPI microservices that serve multiple brand clients simultaneously. I focus on reliable orchestration (LangGraph), rigorous prompt engineering and model evaluation, and practical engineering that turns model outputs into consistent, on-brand production assets.

Experience

Work history, roles, and key accomplishments

Current

AI Engineer

Current

Tagshop AI

Oct 2025 - Present (9 months)

Architected and implemented an end-to-end agentic AI workflow for automated ad creation, including autonomous multi-step reasoning and tool-calling across the creative pipeline. Built multimodal storyboard and Ad-Clone features using Claude and Gemini APIs, and deployed FastAPI microservices plus an AI Twin brand asset pipeline; improved output quality through prompt engineering and model evaluati

Agentic AI Tool calling Multimodal AI Prompt Engineering Model Evaluation fastAPI Claude Gemini API Microservices REST APIs

AI Engineer

Collonmade

Jun 2024 - Oct 2025 (1 year 4 months)

Delivered AI solutions across video, speech, and image domains, handling end-to-end development from model integration to REST API deployment for client applications. Optimized model inference speed and contributed to data processing, model evaluation, and performance tuning to improve reliability and output accuracy.