Responsibilities :

- Design, develop, and deploy production-grade AI and ML systems.

- Build document extraction and classification pipelines for high volumes of data.

- Develop and maintain Retrieval-Augmented Generation (RAG) systems using vector databases and hybrid search techniques.

- Architect multi-tenant AI platforms with tenant isolation, rate limiting, and usage-based cost attribution.

- Optimize LLM inference costs through prompt engineering, caching, tiered model routing, and token reduction strategies.

- Create robust evaluation frameworks and automated test harnesses for LLM applications.

- Measure and improve system quality using precision, recall, F1 score, and other relevant metrics.

- Build multilingual NLP capabilities, particularly for non-Latin languages (Indic languages, Arabic, Mandarin, etc.).

- Collaborate with product, engineering, and platform teams to deliver scalable AI solutions.

- Ensure the reliability, monitoring, observability, and performance of AI services in production.

Required Qualifications :

Education :

- Bachelor's or Master's degree in Computer Science, AI, Machine Learning, or a related field.

- Graduates from IITs, NITs, BITS, IIITs, or equivalent institutions are preferred.

- A Master's specialization in Machine Learning or NLP is a strong advantage.

Experience :

- 5 to 8 years of experience in software engineering, machine learning, or AI.

- Minimum 2 years of hands-on experience building LLM or Generative AI applications.

- Proven experience deploying AI solutions into production environments.