Senior AI Engineer

KEY RESPONSIBILITIESBuild the agent architecture: specialist agents for explanation, memorization, and practice behind a single companion personaBuild the routing layer that knows the student's context and calls the right specialist at the right timeBuild RAG over NCERT and curriculum content, tied to the concept hierarchyMake the companion teach well in Hinglish — tone, empathy, and code-switching that sounds like a real teacherOwn evaluation: is the explanation correct, is it pitched right, did the student actually learn — automated and human-in-the-loopImplement mastery scoring and the logic that decides what a student sees nextOwn guardrails and safety for a student-facing AI, and keep latency and cost in check at scaleREQUIRED SKILLS5+ years in applied ML or NLPStrong Python (PyTorch / TensorFlow / scikit-learn)Hands-on with LLMs: prompt engineering, RAG, embeddings, vector storesBuilt multi-agent or tool-using systems in production, not just demosAbility to design an eval suite, not just run oneCloud ML infrastructure (GCP Vertex AI preferred; SageMaker / Azure ML also fine)Experience taking ML systems from prototype to productionNICE TO HAVEEducation or tutoring products — knowledge tracing, mastery models, spaced repetitionIndian language NLP and Hinglish code-switchingProduction experience with Gemini / Claude / GPT-class modelsSpeech and voice AI (Whisper, Deepgram, TTS)Serving LLMs cheaply at scale — caching, routing, smaller models where they sufficeHOW WE WORKSmall teams with real ownership — you shape how your area works, rather than inheriting a processWe ship fast, measure honestly, and cut what isn't working instead of defending itResearch and data sit next to product here; opinions lose to evidenceAI tooling is part of the workflow for everyone, not just the engineers