11/09/2026 updated
100 % available
AI Backend Engineer | Generative AI & LLM Applications | RAG | FastAPI | Vector Databases
Noida, India
Only remote
Bachelor of Technology (IT)AI AgentsLLMPython (Programming Language)Database EnginesChatbotsReact.jsBackend Programming
Generative AI & LLM Applications
Expertise in building Generative AI systems using Large Language Models (LLMs), Retrieval-Augmented Generation (RAG) pipelines, Prompt Engineering, and Semantic Search with embedding-based retrieval and vector databases such as Qdrant.
FastAPI & Backend Development
Proficiency in designing and developing modular FastAPI backend services, REST APIs, and asynchronous pipelines using Celery and Redis for scalable enterprise AI applications.
Vector Databases & Retrieval Systems
Hands-on experience with vector databases (Qdrant), document ingestion, chunking, embedding generation, and retrieval workflows for context-aware, low-latency document search and semantic memory.
Python Programming
Strong command of Python for AI/ML development, backend services, data processing, and automation, including libraries such as NumPy, Pandas, Scikit-Learn, PyMuPDF, and Whisper.
AI/ML Frameworks & Tools
Experience with LangChain, Hugging Face, model evaluation, document chunking, and multi-LLM consensus approaches combining Groq, OpenAI, and Gemini.
Database Management
Knowledge of relational and non-relational databases including PostgreSQL, MongoDB, and MySQL, as well as vector search and Qdrant-based semantic memory for repository architecture.
DevOps & CI/CD Tools
Familiarity with Docker, Docker Compose, Git, GitHub, GitHub Actions, and Postman for reproducible development, testing, and deployment workflows.
Frontend & Visualization
Experience with Next.js for analytics dashboards, as well as HTML, CSS, Tailwind CSS, and Tableau for data visualization and reporting.
Cloud & Certifications
Oracle Cloud Infrastructure certified as Generative AI Professional and AI Foundations Associate, with practical knowledge of cloud-based AI services and prompt engineering.
Expertise in building Generative AI systems using Large Language Models (LLMs), Retrieval-Augmented Generation (RAG) pipelines, Prompt Engineering, and Semantic Search with embedding-based retrieval and vector databases such as Qdrant.
FastAPI & Backend Development
Proficiency in designing and developing modular FastAPI backend services, REST APIs, and asynchronous pipelines using Celery and Redis for scalable enterprise AI applications.
Vector Databases & Retrieval Systems
Hands-on experience with vector databases (Qdrant), document ingestion, chunking, embedding generation, and retrieval workflows for context-aware, low-latency document search and semantic memory.
Python Programming
Strong command of Python for AI/ML development, backend services, data processing, and automation, including libraries such as NumPy, Pandas, Scikit-Learn, PyMuPDF, and Whisper.
AI/ML Frameworks & Tools
Experience with LangChain, Hugging Face, model evaluation, document chunking, and multi-LLM consensus approaches combining Groq, OpenAI, and Gemini.
Database Management
Knowledge of relational and non-relational databases including PostgreSQL, MongoDB, and MySQL, as well as vector search and Qdrant-based semantic memory for repository architecture.
DevOps & CI/CD Tools
Familiarity with Docker, Docker Compose, Git, GitHub, GitHub Actions, and Postman for reproducible development, testing, and deployment workflows.
Frontend & Visualization
Experience with Next.js for analytics dashboards, as well as HTML, CSS, Tailwind CSS, and Tableau for data visualization and reporting.
Cloud & Certifications
Oracle Cloud Infrastructure certified as Generative AI Professional and AI Foundations Associate, with practical knowledge of cloud-based AI services and prompt engineering.
Experience
Professional experience0 - 5 years
Freelancer since2026
Languages
EnglishNative speaker
Project history
Designed and developed modular FastAPI backend services powering enterprise AI assistants. Built RAG pipelines with semantic retrieval using Qdrant and embedding-based search. Implemented document ingestion, chunking, embedding generation, and retrieval workflows for context-aware responses. Optimized retrieval pipelines for low-latency inference and scalable document search.
Architected an evidence-gated medical question-answering system using RAG, focused on minimizing hallucinations in LLM-generated clinical responses. Engineered claim-level verification pipelines that separate factual outputs from inferential ones. Built end-to-end retrieval grounding and claim-level validation architecture for trustworthy AI-assisted decision support in medical contexts. Technologies: Python, FastAPI, RAG, LLMs, Vector Databases.
Built a full-stack AI code-review platform that automatically analyzes GitHub pull requests using multi-LLM consensus combining Groq, OpenAI, and Gemini. Engineered an asynchronous Celery + Redis review pipeline integrating GitHub webhooks, Bandit/Semgrep security scanning, PR risk scoring, LLM analysis, and semantic memory. Implemented Qdrant-based semantic memory for repository architecture and coding standards. Developed a Next.js analytics dashboard for PR quality, security findings, and developer metrics with Docker Compose and GitHub Actions CI. Technologies: FastAPI, Next.js, Python, Celery, Redis, PostgreSQL, Qdrant, Docker, GitHub APIs.