What are the responsibilities and job description for the GenAI engineer position at Whiztek Corp?
We are seeking a highly skilled GenAI Engineer to lead the development of cutting-edge AI solutions for a major airline client in Chicago. This role is at the intersection of traditional high-performance backend engineering and modern Generative AI. You will be responsible for building the brains of our AI services—architecting robust RAG pipelines, managing vector data at scale, and engineering MCP servers to standardize LLM interactions across the enterprise.
Core Responsibilities
AI Orchestration & RAG Pipelines: Architect and design the backend logic for Retrieval-Augmented Generation (RAG). This includes managing the full lifecycle of vector embeddings, automated data ingestion workflows, and advanced prompt engineering.
Python AI Development: Build and deploy highly scalable microservices using Python (FastAPI/Flask). Optimize these systems for high-performance AI inference and real-time data processing.
MCP Server Engineering: Develop and maintain high-performance Model Context Protocol (MCP) servers to standardize data access and tool-calling across multiple LLM providers (OpenAI, Anthropic, etc.).
Advanced Data Modeling: Manage complex state transitions and data flows between relational databases, AWS Neptune (Graph DB), OpenSearch (Vector Store), and distributed caches (Redis).
Event-Driven Architecture: Implement robust event-driven systems to handle real-time and asynchronous data needs using message brokers such as Solace, SQS, or Kafka.
API & Protocol Mastery: Define contract-first development standards using SSE (Server-Sent Events) and REST to ensure seamless integration between backend AI services and frontend consumers.
Technical Requirements
Primary Language: Expert-level proficiency in Python (specifically for AI/ML application development).
GenAI Expertise: Hands-on experience with Generative AI, vector databases, and designing complex RAG workflows.
Infrastructure: Deep understanding of the AWS ecosystem (Neptune, OpenSearch, SQS) and AWS Serverless architecture.
Messaging: Proven experience with Solace, Kafka, or SQS.
Protocols: Mastery of RESTful APIs and real-time streaming via SSE.
Nice to Have
Heavy experience with LangChain or LlamaIndex.
Familiarity with MCP Python SDKs.
Knowledge of PyTorch or TensorFlow for local model fine-tuning.
Previous experience in the Aviation or Travel industry.