Description

You will build and deploy scalable generative AI solutions for document summarization, anomaly detection, and content extraction.

This role is hybrid.

Responsibilities

• Develop and deploy AI/ML pipelines to ingest and analyze unstructured data, including application logs, usage data, and PDFs.
• Design and implement data processing pipelines that feed into analytical data marts.
• Integrate and optimize vector databases for semantic search and retrieval-augmented generation (RAG) applications.
• Leverage AWS tools including Bedrock, Textract, and Comprehend to automate unstructured data workflows.
• Collaborate with data engineers and stakeholders to transition requirements into production-grade solutions.

Required Skills

• 3+ years of experience in AI/ML engineering with proven production model deployment.
• Proficiency in Python and AI/ML libraries such as PyTorch, TensorFlow, LangChain, and HuggingFace.
• Hands-on experience with generative AI technologies, including LLMs, diffusion models, and RAG systems.
• Practical application of Vector Databases such as FAISS, Pinecone, Weaviate, or Milvus.
• Experience working with application logs, telemetry data, and unstructured documents.
• Knowledge of document parsing, entity extraction, summarization, and topic modeling.
• Familiarity with AWS AI/ML services including Textract, Bedrock, Comprehend, and S3.
• Experience deploying models in containerized environments using Docker and Kubernetes.

Preferred Skills

• Experience in fraud analytics or insurance claims systems.
• Background in data warehousing, data mart design, and MLOps/CI/CD pipelines.

Key Skills

Education

Any Gradute