remote
AI Engineer - WhiztekCorp
AI Engineer
AI Engineer focused on building event‑driven, serverless pipelines that orchestrate Retrieval‑Augmented Generation workflows, manage vector embeddings, and maintain high‑performance MCP servers across multiple LLM providers.
About the role
Key Responsibilities
- Design and implement event‑driven architectures using message brokers such as Kafka, Solace, and AWS SQS to support real‑time and batch data flows.
- Develop AWS Serverless components (Lambda, Step Functions, EventBridge) that integrate with RAG pipelines and vector stores.
- Build and maintain high‑performance MCP servers to standardize data access and tool‑calling across multiple LLM providers.
- Engineer end‑to‑end RAG workflows: ingest data, generate and store vector embeddings, create prompt templates, and orchestrate retrieval and generation cycles.
- Collaborate with data scientists and product teams to refine model prompts, evaluate performance, and iterate on pipeline efficiency.
Requirements
- Proven experience with event‑driven architecture and message brokers (Kafka, Solace, SQS).
- Strong background in AWS Serverless services and architecture design.
- Hands‑on experience building RAG pipelines, managing vector embeddings, and prompt engineering.
- Solid programming skills in Python or Node.js, with familiarity in building high‑throughput servers.
- Excellent problem‑solving skills and ability to work independently in a remote, contract‑based environment.