Looks like you have JavaScript disabled. For the full Twine experience, you will need to re-enable it.

I am an AI Backend Engineer specializing in LLMs, RAG pipelines, multi-agent systems, and high-performance FastAPI services. I design and deploy scalable AI systems with ownership and reliability. I have hands-on experience with vector search (Pinecone, pgvector), hybrid retrieval architectures, ingestion pipelines, orchestration, and production deployments on AWS/OCI. I value collaboration and clear communication to deliver impactful AI solutions.…I am an AI Backend Engineer specializing in LLMs, RAG pipelines, multi-agent systems, and high-performance FastAPI services. I design and deploy scalable AI systems with ownership and reliability. I have hands-on experience with vector search (Pinecone, pgvector), hybrid retrieval architectures, ingestion pipelines, orchestration, and production deployments on AWS/OCI. I value collaboration and clear communication to deliver impactful AI solutions.

Ashwin Deepak Upadhyay

AI Developer, Full Stack Developer, Back-End Developer, +6





I am an AI Backend Engineer specializing in LLMs, RAG pipelines, multi-agent systems, and high-performance FastAPI services. I design and deploy scalable AI systems with ownership and reliability. I have hands-on experience with vector search (Pinecone, pgvector), hybrid retrieval architectures, ingestion pipelines, orchestration, and production deployments on AWS/OCI. I value collaboration and clear communication to deliver impactful AI solutions.…I am an AI Backend Engineer specializing in LLMs, RAG pipelines, multi-agent systems, and high-performance FastAPI services. I design and deploy scalable AI systems with ownership and reliability. I have hands-on experience with vector search (Pinecone, pgvector), hybrid retrieval architectures, ingestion pipelines, orchestration, and production deployments on AWS/OCI. I value collaboration and clear communication to deliver impactful AI solutions.

Available to hire

I am an AI Backend Engineer specializing in LLMs, RAG pipelines, multi-agent systems, and high-performance FastAPI services. I design and deploy scalable AI systems with ownership and reliability.

I have hands-on experience with vector search (Pinecone, pgvector), hybrid retrieval architectures, ingestion pipelines, orchestration, and production deployments on AWS/OCI. I value collaboration and clear communication to deliver impactful AI solutions.

Skills

Experience Level

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Intermediate

Intermediate

Intermediate

Language

English

Advanced

Work Experience

AI/ML Solutions Developer (Internship) at Smartek21

February 1, 2024 - August 1, 2024

Built LLM/RAG pipelines using LangChain and pgvector, improving retrieval accuracy by 20%. Developed PyTorch training workflows and reduced deployment time by 40% using MLflow. Created FastAPI microservices with FAISS search for low-latency inference across 10k+ embeddings. Built a structured prompt-evaluation harness improving LLM output quality by 18%.

Freelance Backend Engineer at Pinecone Automated Foldering System

November 25, 2025 - January 26, 2026

Led end-to-end engineering of a multi-tenant, matter-isolated RAG backend using FastAPI, Pinecone, PostgreSQL, Redis/RQ, and Nginx. Built hybrid retrieval with BM25 + Voyage embeddings + RRF fusion + cross-encoder reranking, improving accuracy from ~20% to 80–90%. Designed scalable ingestion for 100+ parallel documents with ZIP expansion (20+ formats), SHA-256 dedup, and metadata extraction. Reduced vector storage cost by 30–40% through document and chunk-level deduplication. Implemented folder-level BM25/vector isolation enabling clean retrieval for Claude MCP and N8N workflows. Delivered 2,000+ lines of automated tests covering ingestion, metadata, namespaces, folders, performance, and query correctness. Production deployment included RQ worker autoscaling, systemd automation, staging smoke tests, ingestion dashboards, and admin tooling.

ML Engineer / Backend Engineer at FinAgent

June 25, 2025 - October 25, 2025

Engineered a LangGraph-based multi-agent system with agents for data processing, risk scoring, anomaly detection, insight generation, collaboration, and visualization. Implemented RAG ingestion + LLM reasoning for natural language financial insights and report generation. Built fraud detection using Isolation Forest and supervised ML pipelines, with explainability and risk summaries. Developed FastAPI backend and Streamlit dashboard with real-time transaction streaming and alerting. Added caching, workspace collaboration, visualization APIs, and a unified test suite for reliability.

RAG Engine Architect / Backend Engineer at Cerevra

November 25, 2025 - Present

Architected a production-grade RAG engine with WAL-backed ingestion and strict namespace isolation, ensuring 100% data consistency across 500+ restart scenarios. Built sharded BM25 indexing with hybrid retrieval supporting 10K+ documents per namespace, achieving sub-300ms query latency through adaptive ranking and context windowing. Engineered robust observability with 2,500+ lines of automated tests, Prometheus metrics, and admin tooling for production deployment on Railway.

Freelance ML Consultant at Independent / Freelance

January 25, 2025 - February 25, 2025

Delivered end-to-end ML solutions for clients including time series forecasting and classification models, reducing operational costs by 25% through automated predictive analytics. Spearheaded data strategy initiatives, implementing feature engineering pipelines and model deployment workflows that improved decision-making accuracy by 40%.

Education

Bachelor of Engineering (Information Technology) at Savitribai Phule Pune University, Pune

January 1, 2021 - January 1, 2025

Bachelor of Engineering (Information Technology) at Savitribai Phule Pune University, Pune

January 1, 2021 - January 1, 2025