AI Engineer (RAG Specialist)

About Amogha AI

At Amogha AI, we are building India’s first voice-led conversational AI app specifically for mental health, therapy, and emotional well-being. Our mission is to provide a supportive, empathetic listener in your pocket, 24 / 7. We are creating a next-generation product that understands user context, provides therapy-grade support, and guarantees 100% safety and privacy—a truly specialized application far beyond a generic ChatGPT experience.

The Opportunity

As a AI Engineer specialising in RAG, you will architect our AI's 'mind.' We are processing a unique and sensitive proprietary dataset of therapy transcripts to build a system that can reason, understand complex therapeutic context, and provide responses that are not just accurate, but also empathetic and safe. The foundational implementation of our RAG pipeline is complete. We are now looking for a RAG specialist to join our team, take ownership of this advanced architecture, and help us complete, refine, optimize, and scale this system for a production environment.

What You'll Do

• Optimize Hybrid Retrieval : Tune our existing retrieval stack for maximum speed & contextual accuracy.
• Refine Data Processing : Optimize the LLM-powered "Intelligent Chunking" logic to perfectly preserve therapeutic and emotional continuity.
• Optimize Feature Engineering : Refine and optimize our multi-model pipeline (using small transformers) for extracting key features from each chunk (e.g., emotion, crisis flags etc).
• Tune AI Gateway : Optimize the Two-Stage AI Processing logic, refining the intelligent routing between cost-effective (Stage 1) and premium (Stage 2) models for cost and quality.
• Implement Evaluation : Build and run a robust evaluation framework (A / B testing, etc.) to validate retrieval accuracy, response quality, and crisis detection effectiveness.
• Build Learning Loops : Deploy the Continuous Learning Framework, implementing feedback loops and reinforcement learning (RL) components to improve the system's performance.
• Enhance Monitoring & Explainability : Implement the real-time monitoring dashboard (health, latency, cost) and the Explainability Framework (audit trails, confidence scores).
• Scale for Production : Lead system-wide optimization, including caching strategies, to ensure high scalability and performance.

What We're Looking For

Contract : 2–3 months (will translate to full-time with equity) | Remote / Hybrid | Competitive compensation