Key Responsibilities :

- Design, develop, and deploy scalable AI and data science applications using Python and modern software engineering practices.

- Build production-ready APIs and backend services using FastAPI, Flask, or similar frameworks, including REST APIs and asynchronous processing.

- Develop LLM-powered applications using foundation models, embeddings, prompt engineering, tool calling, function calling, and structured outputs.

- Design and implement RAG architectures, including data ingestion, document processing, chunking, embedding generation, retrieval, ranking, grounding, citations, and evaluation.

- Work with vector databases and search technologies to build efficient semantic search and retrieval solutions.

- Design and implement prompt strategies, evaluation frameworks, and techniques to reduce hallucinations and improve LLM response quality.

- Apply LLM security practices including protection against prompt injection, data leakage, unauthorized access, and insecure model interactions, along with appropriate guardrails.

- Implement MLOps/LLMOps practices covering model and application deployment, versioning, monitoring, evaluation, observability, and lifecycle management.

- Collaborate with Data Scientists, ML Engineers, Software Engineers, Product teams, and business stakeholders to translate requirements into scalable AI solutions.

- Troubleshoot, optimize, and continuously improve AI applications for performance, reliability, scalability, security, and cost efficiency.

Required Skills & Experience :

- 6 to 9 years of experience in Data Science Engineering, Machine Learning Engineering, AI Engineering, or a related field.

- Strong hands-on expertise in Python.

- Experience developing APIs using FastAPI, Flask, or similar frameworks.

- Strong understanding of REST APIs and asynchronous processing.

- Hands-on experience in LLM application development.

- Strong understanding of LLM concepts including embeddings, vector search, prompt design, evaluation, and hallucination control.

- Hands-on experience implementing RAG architectures.

- Experience with vector databases and semantic search.

- Understanding of prompt engineering, tool calling, function calling, and structured outputs.

- Knowledge of MLOps / LLMOps fundamentals, including deployment, monitoring, versioning, evaluation, and observability.

- Strong understanding of LLM security, including prompt injection, data leakage, access control, and guardrails.

- Strong problem-solving, analytical, communication, and collaboration skills.