Role Summary
Build intelligent capabilities using LLM-based inferencing, agentic AI workflows, and RAG-based solutions leveraging AWS-native AI/ML services. Focus on inference orchestration, vector search pipelines, and lightweight model training for predictive maintenance use cases.
Key Responsibilities

LLM & Inference Engineering:
Develop AI-driven features using LLMs, agentic patterns, RAG, and vector embeddings.
Orchestrate inference pipelines with Python and AWS AI services.
Build reusable components and prompt orchestration flows.

Predictive Analytics & Light Model Training:
Support predictive maintenance using classical ML techniques.
Perform lightweight training with AWS SageMaker, AutoML, and deploy inference endpoints.

AWS Engineering:
Utilize AWS services (Lambda, API Gateway, S3, DynamoDB, SageMaker, Bedrock) for scalable AI workflows.

Python Development:
Write modular, testable Python code for inference orchestration and backend integrations.

Collaboration & Delivery:
Work with product and engineering teams; document AI workflows; participate in design reviews.

Must-Have Skills
Strong proficiency in Python.
Hands-on experience with LLM inferencing, RAG architectures, and vector embeddings.
Working knowledge of AWS AI/ML services (SageMaker, Bedrock, Lambda, etc.).
Familiarity with classical ML concepts (regression, classification, anomaly detection).
Experience integrating models into production pipelines.
Understanding of prompt engineering and evaluation.