• 3+ years of experience in AI/ML engineering, with proven deployment of models in production.
• Proficiency in Python and relevant AI/ML libraries (e.g., PyTorch, TensorFlow, LangChain, HuggingFace).
• Hands-on experience with generative AI technologies (e.g., LLMs, diffusion models, RAG systems).
• Solid understanding and application of Vector Databases (e.g., FAISS, Pinecone, Weaviate, Milvus).
• Demonstrated ability to work with application logs, telemetry data, and unstructured documents (e.g., PDFs, text logs).
• Knowledge of document parsing, entity extraction, summarization, and topic modeling techniques.
• Familiarity with AWS AI/ML tools, particularly Textract, Bedrock, Comprehend, and S3.
• Experience deploying ML models in containerized environments (e.g., Docker, Kubernetes).

Roles & Responsibilities

• Develop and deploy AI/ML pipelines that ingest and analyze unstructured data (e.g., application logs, usage data, PDFs). Build and maintain scalable solutions using generative AI models for tasks such as document summarization, anomaly detection, and content extraction. 
• Design and implement data processing pipelines feeding into analytical data marts. 
• Integrate and optimize vector databases for semantic search and retrieval-augmented generation (RAG) applications.
• Collaborate closely with data engineers and business stakeholders to translate requirements into production-grade solutions. 
• Leverage AWS tools (e.g., Bedrock, Textract, Comprehend) to implement AI-powered features and automate unstructured data workflows. 
• Contribute to the team’s Agile practices including sprint planning, backlog grooming, and demos.