Senior AI | GenAI Engineer (Agentic & Multimodal Systems)

Location: Remote / Hybrid Experience: 1-2 Years Employment Type: Full-Time **About the Role** We are building next-generation AI systems that operate in real-world environments — combining agentic reasoning, predictive intelligence, multilingual voice interfaces, and intelligent routing. We are looking for a Senior AI | GenAI Engineer who can architect and deploy advanced multi-agent systems capable of planning, recommendation, contextual reasoning, and real-time adaptation. This role goes beyond simple LLM integrations. You will design AI systems that think, decide, allocate, optimize, and interact across modalities. **What You’ll Build** Multi-agent AI systems using modern LLM ecosystems (including Claude) MCP-based structured context architectures Intelligent planning and reasoning agents Real-time routing and decision-support engines AI-driven recommendation and allocation systems Multilingual conversational AI (text + voice) Predictive and optimization models for real-world workflows Multimodal content intelligence systems (text, image, video, audio) **Key Responsibilities** 1️⃣ Agentic Architecture & LLM Systems Design and implement multi-agent systems with memory, tools, and orchestration Build structured context pipelines using MCP Implement reasoning-driven workflows across dynamic environments Integrate LLMs with external APIs, databases, and live signals 2️⃣ Prediction, Recommendation & Allocation Develop intelligent matching and ranking systems Build recommendation engines based on profile, history, and contextual signals Design predictive models for demand, allocation, and optimization Implement decision engines that adapt to real-time changes 3️⃣ Real-Time Routing & Navigation Intelligence Build AI systems that analyze: Traffic Weather Density / crowd signals Scheduling constraints Optimize routes and sequencing dynamically Improve user experience through adaptive planning 4️⃣ Voice & Indian Language AI Build multilingual conversational systems Implement STT and TTS pipelines Ensure fluency and contextual accuracy in Indian languages Design voice-first AI workflows 5️⃣ AI Assessment & Performance Intelligence Build scoring and evaluation systems Design AI-driven performance insights Develop profile intelligence frameworks Implement feedback-loop learning systems 6️⃣ Multimodal AI & Content Intelligence Build pipelines for: Text generation Audio intelligence Video analysis Image understanding Implement AI moderation and safety systems Detect inappropriate or unsafe content across modalities **Technical Requirements** **Must Have:** Strong experience with Claude or similar advanced LLM ecosystems Deep understanding of MCP (Model Context Protocol) Experience building multi-agent AI systems Strong Python expertise Experience with: RAG architectures Vector databases Embeddings Tool-augmented agents **Experience in:** Recommendation systems Predictive modeling Optimization algorithms Experience building production-grade AI systems **Strong Plus:** Experience with: Voice AI systems (STT / TTS) Indian language NLP Geo-spatial systems Real-time signal processing Computer vision pipelines Background in marketplace or allocation engines Experience deploying scalable AI infrastructure (AWS/GCP/Azure) **What We’re Looking For** Systems thinker, not just prompt engineer Strong problem-solving & architecture skills Ability to move from concept → production Comfortable working with ambiguity High ownership mindset Interested in building applied AI with real-world impact **Why Join** Build advanced agentic AI systems beyond basic chatbots Work on real-time intelligence + decision-making AI High autonomy and technical ownership Opportunity to define scalable AI infrastructure from scratch