Sonam S.

Need an AI agent, RAG pipeline, or voice bot built right the first time? I build production-grade LLM systems using Python, LangChain, LlamaIndex, OpenAI, and Gemini. Fully integrated and deployed, not just prototyped. [ WHAT I BUILD ] ▸ AI Agents and multi-agent systems (LangChain, CrewAI, AutoGen) ▸ RAG pipelines with ChromaDB, Pinecone, and Weaviate ▸ Voice AI agents with ElevenLabs, Twilio, and AssemblyAI ▸ LLM integrations via OpenAI, Claude, Gemini, and Mistral APIs ▸ n8n and Zapier automations connecting AI to your business tools ▸ Fine-tuned models on Hugging Face for domain-specific tasks ▸ Conversational chatbots for support, sales, and internal tools [ TECH STACK ] Language: Python LLM Frameworks: LangChain, LlamaIndex, CrewAI, AutoGen LLM APIs: OpenAI, Claude, Gemini, Mistral, Hugging Face Vector DBs: ChromaDB, Pinecone, Weaviate Voice AI: ElevenLabs, Twilio, AssemblyAI Automation: n8n, Zapier Deployment FastAPI, Docker, AWS, GCP [ HOW I WORK ] ▸ I scope your problem first and tell you what is technically feasible before writing a single line of code ▸ I build lean, no bloated frameworks, no over-engineering ▸ I respond within a few hours and keep communication clear throughout ▸ Most clients come back for the next project [ RECENT WORK ] ▸ Multi-agent research assistant (production) ▸ Voice-enabled appointment bot for a healthcare client ▸ Document Q&A system with RAG for a SaaS platform Available for project-based work and ongoing retainers. Send me a message with what you are building. I will give you a straight assessment within a few hours.