Applied AI Engineer

InTecAir, Inc. is hiring an Applied AI Engineer to build reliable, practical AI features for airline employees and customers by shipping LLM-based applications grounded in company knowledge and business systems.

Responsibilities

• Build and maintain an AI knowledge corpus by collecting, cleaning, organizing, and updating documents and structured data while preserving sources, versions, and access permissions
• Advance retrieval-augmented generation (RAG) with work across document processing, embeddings, search, and the quality of retrieved information sent to models
• Integrate and maintain model pipelines, including Qwen for vision and Gemma for answer generation
• Support local deployment on Apple silicon and related performance and reliability improvements
• Collaborate with application developers on Apple Intelligence and the Foundation Models framework
• Develop Model Context Protocol (MCP) and API integrations for customer-facing services such as flight schedules, fare search, and booking workflows using authoritative business systems for up-to-date information
• Create repeatable evaluations, investigate incorrect outputs and integration failures, and improve accuracy, response time, and reliability
• Document work and build maintainable systems with appropriate security, privacy, and monitoring

Requirements

• Demonstrated ability to build working software, including an LLM application, retrieval system, AI integration, or a substantial related project
• Strong programming and debugging skills, especially in Python, with experience using APIs, processing data, and working with Git
• Practical understanding of how language models use retrieved information and tools, including common limitations
• Ability to translate an unclear business request into an implementable plan and clearly explain technical decisions
• Care with source accuracy, handling confidential information, and testing
• Independence, curiosity, and willingness to maintain and improve what you build

Technologies

• Python
• Qwen
• Gemma
• Retrieval-augmented generation (RAG)
• Embeddings
• Search
• Apple silicon
• Apple Intelligence
• Foundation Models framework
• Model Context Protocol (MCP)
• APIs
• Swift
• iOS/macOS
• MLX
• Vector search
• Reranking
• Automated evaluations
• Tool calling
• Authentication

Helpful Experience

• Qwen, Gemma, or comparable open-weight models
• RAG pipelines, vector search, reranking, and automated evaluations
• MCP servers, tool calling, authentication, and business-system integrations
• Swift, iOS/macOS development, Apple Intelligence, Foundation Models, or MLX
• Local or offline AI deployment, multilingual applications, document processing, or computer vision
• Airline, travel, commerce, or other operational systems

Benefits

• 401(k)
• Dental insurance
• Health insurance
• Paid time off
• Vision insurance

Location: Palo Alto, CA (onsite)

Salary: USD 150,000 - 175,000 per yearly

How We Work

• Encourage using AI tools for development, research, documentation, and content preparation
• Expect comfort using AI tools to move faster while understanding, testing, and taking responsibility for the resulting work
• Role includes direct ownership, access to real airline problems, and opportunity to help shape a growing internal AI capability