Generative AI Engineer

Location: Delhi NCR / Hybrid (India)

Experience: 37+ years (strong hands-on experience required)

Type: Full-time

Product: Consumer AI Tutor Platform (YoLearn.ai)

We are building a real-time, conversational AI tutor used by students daily not demos, not prototypes.

This role combines:

• Generative AI Engineering
• AI Agent & Multi-Agent Systems
• Conversational Voice / Video AI
• Backend & API Engineering

You will work on low-latency, high-throughput AI systems that power talking AI tutors with memory, personalization, and real-time interaction.

If youve shipped real AI products to users and care about latency, cost, reliability, and learning outcomes this role is for you.

• AI tutor agents (teacher, evaluator, planner, motivator)
• Multi-agent orchestration for learning workflows
• Real-time voice & video AI conversations
• Student personalization & long-term memory systems
• Agent APIs used by millions of requests
• Evaluation pipelines to continuously improve AI quality

We are explicitly looking for hands-on builders, not theory-only profiles.

• Experience working on LLM agents with high throughput and low latency
• Experience building low-latency multimodal (text, voice, video) input & output agents
• Strong understanding of agent architectures (ReAct, planner-executor, tool-using agents)
• Hands-on with LangGraph, LangFlow, CrewAI, AutoGen or similar frameworks

• Strong background in context engineering and prompt engineering pipelines
• Experience designing:
• System prompts
• Dynamic context injection
• Memory-aware prompts
• Token budgeting, cost control, hallucination mitigation

• Hands-on experience building and deploying RAG pipelines
• Experience with vector databases (Pinecone, Weaviate, Qdrant, Milvus)
• Strong experience with NoSQL databases (critical for learning paths & memory layer)
• Designing short-term vs long-term memory for users

• Real-time conversational Voice AI
• Speech-to-Text & Text-to-Speech pipelines
• WebRTC, streaming audio/video
• Latency optimization & streaming inference
• Experience building talking AI tutors / conversational agents

• Strong fundamentals in Python
• Experience building Agent APIs
• Token usage tracking, metering & rate limiting
• Strong fundamentals in Python, SQL, Redis, and API development
• REST / gRPC APIs using FastAPI or similar

• Experience designing and maintaining AI evaluation pipelines
• Offline & online evaluation (quality, latency, cost)
• Familiarity with CI/CD pipelines and production deployment workflows
• Has shipped real AI products to production users

• Experience with consumer AI products (education, companions, assistants)
• Experience with personalization systems
• Frontend collaboration for real-time AI UX
• Experience working with GPU-backed inference systems

• 15 25 LPA (MidSenior)
• 25 35+ LPA (Strong Senior / Lead)
• Compensation structure: 80% cash in hand , 20% ESOP

• You think in systems, not just prompts
• You care about latency, cost, reliability
• Youve built AI features people actually use
• Youre excited about consumer AI at scale