Satyam Namdev

ezAIx, Inc · Thousand Oaks, USA (Remote)

• –Lead engineer & architect of VoiceCoreIQ — 30+ Django ASGI apps (80K+ lines of Python) on Azure Communication Services for call automation, queue routing, IVR, agent presence and analytics.
• –Built the AI Voicebot bridging Azure OpenAI GPT-4o Realtime with ACS media streams — tool calling (order lookup, CSAT, RAG search), per-session cost tracking, and deterministic human handoff.
• –Integrated a per-voicebot RAG knowledge base: Azure Document Intelligence parsing, 512-token chunking, hybrid search on isolated Pinecone namespaces, plus AI KB gap detection that auto-drafts articles.
• –Delivered AI Copilot real-time agent assist — live transcript tap, per-utterance sentiment, suggestions over WebSocket/SSE, and a used/dismissed feedback loop.
• –Owned Warm Transfer with Full Context — async (Celery) AI summary, sentiment, intent and next step from the live Redis transcript buffer, pushed with the call offer so callers never repeat themselves.
• –Built the Supervisor Command Center backend — whisper coaching, Redis sentiment heatmap, escalation predictor, burnout detection (Celery Beat), and Firebase-secured listen/barge/whisper APIs.
• –Engineered real-time infrastructure: Django Channels, custom ASGI SSE middleware, Microsoft Graph presence subscriptions, and a Celery call-dispatch state machine; authored a platform scalability audit and phased roadmap.
• –Integrated Oracle Fusion CTI pop-up, ServiceNow deep links and Microsoft Teams transfer; designed multi-tenant MongoDB analytics (16 agent-analytics APIs).
• –Acted as Product Lead on client calls — wrote design docs and drove backend decisions.
• –Flew to Dubai (Dec 17–22, 2025) for the company kickoff — selected engineers and founders gathered in person for a week of strategy and planning.

TunableLabs, LLC · San Francisco, USA (Remote)

• –Built end-to-end Legal-AI system — FastAPI backend, Next.js frontend, Supabase (PostgreSQL) for multi-tenant chat sessions and document collections.
• –Designed LangGraph-based Entity Extraction Agent with schema validation and multi-agent orchestration across 5,000+ legal documents.
• –Implemented multi-LLM orchestration, streaming responses, and real-time WebSocket updates; integrated live web search via Tavily and Exa APIs.
• –Refactored a tightly coupled Gradio monolith into a modular FastAPI backend, enabling scalable API integration across multiple law firms.

Multi-turn streaming RAG chat over 468 curated ideas with multi-provider failover across Groq Llama 3.3 70B and Gemini 2.0 Flash. Built a custom inference logging SDK for latency, token usage, errors, and PII redaction per request, plus an observability dashboard with real-time metrics and Langfuse traces.

Multi-agent system using LangGraph to automate medical case analysis — processing 500+ patient notes, lab reports (LlamaParse), and radiology images (Llama 4 vision) with 94% accuracy. SOAP notes and diagnostic suggestions in under 3 seconds.

Custom-trained YOLOv8s on 5,493 images — 90% detection accuracy. OpenStreetMap API integration to map 1,000+ km of road data for geolocated pothole reporting. Dockerized deployment.