m
manan_jain24

Manan J

@manan_jain24

Software Engineer I

India
Inglés, Hindi
Parte de la información aparece en idioma inglés.
Sobre mí
I am a Software Engineer with extensive experience in Java, Spring Boot, and AI-driven systems. I specialize in building production-grade ERP integrations, RAG systems, and MLOps pipelines. I have a strong background in developing scalable backend architectures and deploying LLM-based agents across AWS and GCP environments.... Lee más
m
manan_jain24
Manan J
desconectado • 
Tiempo medio de respuesta: 1 hora

Revisa mis servicios

Sitios web y software con IA
I will develop custom ai agents and generative ai applications
DeUSD 40 / proyectoMás información

Experiencia laboral

Not Found

Tiempo completo • 1 yr 1 mo

Software Engineer

Jan 2026 - Present • 8 mos

Designed and developed production-grade ERP integrations using Java and Spring Boot by applying object-oriented design principles, SOLID principles, and RESTful architecture, enabling secure, scalable, and maintainable enterprise applications • Implemented secure authentication and authorization workflows using OAuth 2.0, OAuth, and PFM authentication mechanisms with public/private key certificates, ensuring secure API communication across multiple third-party ERP platforms. • Owned end-to-end push/pull synchronization for Timesheets, Projects, Cost Codes, Vendors, and financial entities while collaborating with product, integration, and customer teams to ensure downstream data integrity, seamless cross-platform workflows, and high system reliability. • Leveraged webhooks for real-time event processing and implemented scheduled synchronization using Quartz Scheduler to build fault-tolerant, event-driven integrations that maintained consistent data across distributed enterprise systems.

AI Engineer Intern

Jul 2025 - Dec 2025 • 5 mos

Optimized enterprise AI evaluation pipelines, reducing processing time from one hour to under five minutes per evaluation template while improving operational efficiency by 92% across production workloads. • Developed production-ready conversational AI agents using Pipecat, LangChain, Retrieval-Augmented Generation (RAG), tool calling, and LLM orchestration to automate medical appointment scheduling. • Engineered Docker, Jenkins, and AWS-AMI-based deployment pipelines for LLM-as-a-Judge evaluation agents, improving deployment reliability, reproducibility, and release efficiency across multiple environments.