Opportunity brief
About the Company
RetroGrade AI, from the House of JOTHISHI, is building an intelligent AI-powered Vedic Astrology platform that combines traditional Jyotisha knowledge with modern Artificial Intelligence.
This is an opportunity to work on an AI product where LLMs, astrology knowledge, structured planetary data, RAG, APIs, prompt engineering, and conversational AI come together to create personalized astrological experiences.
We are looking for an AI Engineer who is passionate about Generative AI, Large Language Models, intelligent systems, and building real-world AI products.
Responsibilities
- Build and improve LLM-powered applications for RetroGrade AI.
- Develop and optimize RAG (Retrieval-Augmented Generation) pipelines.
- Integrate and work with LLMs such as Gemini, OpenAI, and other leading models.
- Develop sophisticated prompt engineering and context engineering systems.
- Integrate astrology APIs and structured planetary and horoscope data with AI models.
- Build semantic search, embeddings, and knowledge retrieval systems.
- Develop AI agents, tool-calling workflows, and intelligent automation.
- Create and maintain APIs and backend services connecting AI models with the application.
- Improve response accuracy, consistency, relevance, and latency.
- Design systems for AI evaluation, hallucination reduction, and response quality monitoring.
- Experiment with different models, prompts, RAG strategies, and AI architectures.
- Work with large volumes of structured and unstructured Vedic Astrology knowledge.
- Help build a scalable AI architecture capable of serving users globally.
- Collaborate with developers, astrologers, product managers, and domain experts.
Requirements
We are looking for someone who doesn't simply know how to call an AI API. You should be someone who can ask, "How can we make the AI better?"
You should enjoy experimenting, testing, debugging, and improving AI systems. You should be comfortable moving between code, APIs, prompts, data, models, and product requirements.
A strong candidate will be curious, analytical, entrepreneurial, and excited about building something from the ground up.
Required Skills
Core Engineering
- Strong Python programming skills.
- Experience with REST APIs and backend development.
- Strong understanding of software development fundamentals.
- Experience with Git/GitHub.
- Understanding of databases and data structures.
Generative AI
- Hands-on experience with LLMs and Generative AI.
- Experience with LLM APIs such as Gemini, OpenAI, Claude, or similar platforms.
- Strong prompt engineering skills.
- Understanding of context engineering and LLM application architecture.
- Experience with RAG, embeddings, and semantic search.
- Familiarity with vector databases such as pgvector, Pinecone, FAISS, Weaviate, or similar.
- Experience with LangChain, LangGraph, LlamaIndex, or similar frameworks is preferred.
AI Product Development
- Experience integrating AI into real-world applications.
- Understanding of model evaluation and AI quality improvement.
- Ability to debug AI outputs and identify hallucination, retrieval, and context issues.
- Understanding of AI agents, function/tool calling, and workflow orchestration is an advantage.
- Experience with Docker, cloud platforms, and production deployment is preferred.
Highly Preferred Skills
- Vedic Astrology / Jyotisha
- Astrology APIs
- Horoscope or birth-chart systems
- Knowledge graphs
- Recommendation systems
- Conversational AI / AI chatbots
- Voice AI
- Agentic AI
- Fine-tuning / model adaptation
- MCP (Model Context Protocol)
- LangGraph / LangChain
- Google Gemini / Vertex AI
- Supabase / PostgreSQL / pgvector
- AWS / GCP / Vercel
- AI observability and evaluation platforms
Experience
- Preferred: 1–4 years of hands-on experience in AI Engineering, Generative AI, Machine Learning, Backend Engineering, or related fields.
- Strong candidates with exceptional projects, GitHub work, research, or demonstrated hands-on Generative AI experience may also be considered regardless of conventional experience.