Open to opportunities

Vishnu M

@vishnum1

Message

AI Engineer building production-ready LLM and real-time voice AI systems that automate workflows and improve relevance.

India

Message

What I'm looking for

I’m looking for a role where I can build secure, production-ready AI products—RAG, voice agents, and ML pipelines—with strong observability, evaluation, and fast iteration to deliver measurable impact.

I’m an AI Engineer focused on shipping production-grade AI products—especially RAG systems, real-time voice workflows, and secure LLM experiences that teams can trust.

At Datanetiix, I’m developing a real-time AI Enquiry Voice Bot using LiveKit, Twilio SIP Trunking, Whisper (STT), and Piper (TTS). I also built automated call summarization pipelines that extract customer intent and distribute insights via automated email notifications, while monitoring quality with Langfuse.

I’ve delivered high-impact retrieval and ranking solutions, including a Smart Contact Recommendation Platform used by 100+ C-Suite users. By combining hybrid retrieval and AI-based reranking with Vertex AI Embeddings and Gemini models, I optimized recommendation quality to an 89% Precision@10 score.

I care about reliability and safety: I implement PII redaction, prompt injection guardrails, rate limiting, and role-based document access controls. I also build end-to-end solutions—from IoT ingestion with AWS IoT Core and AWS Lambda to medical, resume, and video learning assistants—often with human-in-the-loop review, audit trails, and observability.

Experience

Work history, roles, and key accomplishments

Current

AI Engineer

Current

Datanetiix

Sep 2025 - Present (9 months)

Developed a real-time inbound voice AI MVP using LiveKit, Twilio SIP trunking, Whisper (STT), and Piper (TTS), plus automated call summarization that extracts intent and sends email insights. Built multiple production-ready AI systems including hybrid RAG report generation and a contact recommendation platform optimized to 89% Precision@10, with secure guardrails and LLM observability via Langfuse

LiveKit SIP Trunking Whisper STT Piper TTS Langfuse OpenAI Text Embedding 3 Large AWS IoT Core

AI Engineer / Project Lead

MedSixty

Mar 2025 - Sep 2025 (6 months)

Led development of a GenAI system that helps doctors answer medical queries, including prompt workflows for translation and information extraction. Implemented a RAG backend using OpenAI for embeddings and LanceDB as the vector store, and worked on backend/frontend integration with improved deployment practices.

OpenAI LanceDB Pydantic Streamlit RAG Embeddings Prompt Engineering Backend Integrations Deployment

AI Engineer

MedSixty

Jan 2025 - Mar 2025 (2 months)

Built an internal AI learning assistant that generates medical scripts to help learners recall topics in under 2 minutes. Produced conversation scripts modeled on a senior doctor explaining topics to residents and answering critical questions.

OpenAI Pydantic QA Driven Responses Educational Content Automation

AI Engineer

MedSixty

Oct 2024 - Dec 2024 (2 months)

Created an AI system to extract key information from news articles and research papers and generate value-packed summaries for doctors. Tuned prompt workflows to produce structured, actionable outputs for medical review.

OpenAI Streamlit Pydantic Structured Outputs