09/23/2026 updated


100 % available
AI/ML Engineer | Full Stack AI Developer | LLM, RAG, Voice AI
New Delhi, India
Worldwide
M.sc in Big Data System (AI/ML)About me
AI Engineer with 11+ years in IT, specializing in AI assistants, chatbots, and Voice AI systems. Strong in building real-time, scalable solutions using FastAPI, WebSockets, and RAG pipelines, with a practical focus on performance, reliability, and business impact.
RAGLLMGeminiFine-TuningData AnalysisUser Interface DesignPython (Programming Language)Machine LearningNext.jsWordPressGoogle CloudFastAPIFull Stack DevelopmentApi DesignRestful Api
I am a Full Stack AI Developer with 10+ years of experience in building and supporting production systems, now focused on developing AI-powered applications using LLMs, RAG architectures, and real-time voice systems.
I have built and deployed production-grade AI solutions including a RAG-based assistant handling 700–1000 daily users and a real-time Voice AI platform using WebRTC and WebSockets for live interaction. My work involves designing end-to-end pipelines including data ingestion, embeddings, retrieval, and LLM orchestration.
I specialize in building scalable backend systems using Python (FastAPI), integrating APIs, and optimizing performance through async processing, caching, and efficient model routing. I also work with vector databases and implement evaluation pipelines to improve response accuracy and reduce hallucinations.
With a strong background in product support, I bring a practical approach to debugging, system reliability, and solving real-world production issues.
I am currently focused on building AI assistants, chatbots, Voice AI systems, and automation tools that deliver real business value.
Experience
Professional experience0 - 5 years
Freelancer since2024
Languages
EnglishFluentHindiNative speakerRussianBasic knowledge
Project history
Built and deployed a production-grade RAG-based AI assistant for Vedic astrology insights, serving 700–1,000 daily users. Designed end-to-end pipeline including data ingestion, embeddings, vector search (Qdrant), and response generation.
Implemented LangGraph-based orchestration for multi-step workflows including retrieval, chart calculations, and contextual response generation. Developed session-based memory for personalized multi-turn conversations.
Engineered backend using Python (FastAPI, async APIs) and integrated with frontend for real-time interactions. Optimized latency, token usage, and response quality through caching, prompt tuning, and selective model routing.
Established evaluation pipelines to improve grounding and reduce hallucinations. Managed deployment using Docker and ensured system reliability, scalability, and performance monitoring.