AI Engineer

Responsibilities:

• Design and develop the Context Layer the central personalization engine powering our AI chat, horoscope, and other modules.
• Build context management frameworks that aggregate and interpret user data, Kundli insights, and planetary transits into reusable personalization profiles.
• Implement multi-turn conversational pipelines with persistent user context (session memory, persona, mood, astrological state).
• Architect and maintain RAG-based knowledge retrieval systems using vector databases.
• Orchestrate LLM pipelines that combine astrological data, user history, and real-time transits to generate personalized responses.
• Integrate context APIs that serve other services (Horoscope, Panchaang, Muhurat) to ensure consistent personalization across the app.
• Work on observability and evaluation frameworks to measure chat quality, personalization depth, and emotional tone.

Requirements:

• 1-3 years experience as an AI Engineer / LLM Developer / Conversational AI Engineer.
• Proficiency in Python and experience with LangChain / LlamaIndex / Transformers.
• Understanding of LLM orchestration, context memory, and RAG architectures.
• Experience designing or maintaining APIs or context stores shared across multiple backend services.
• Good understanding of vector databases (Qdrant, Pinecone, FAISS) and embedding-based retrieval.
• Exposure to OpenAI, Gemini, Claude, Qwen, or Mistral APIs for LLM-based applications.
• Working knowledge of FastAPI, Docker, and AWS ECS / Lambda / CloudWatch.
• Comfort collaborating with ML engineers, backend teams, and domain experts.

Bonus Points:

• Experience with user personalization systems (recommendation, profile inference, or memory graphs).
• Understanding of Hindi or Indic NLP (translation, summarization, tone control).
• Background or interest in astrology, spirituality, or cultural-tech experiences.
• Experience deploying AI chat systems or LLM-backed microservices.
• Familiarity with RAG evaluation metrics or prompt testing pipelines.