Signature Aviation
At Signature Aviation, we are modernizing operations and customer experiences through technology and AI. We are seeking a Senior Engineer – AI Platforms to help design, build, and implement AI-driven solutions that support intelligent automation, predictive insights, and AI-enabled workflows. In this role, you will contribute to the development of LLM-based applications and AI integrations across enterprise platforms, partnering closely with architects, product teams, and data teams to deliver secure, scalable, and responsible AI solutions.
Responsibilities
Evaluate AI Technologies:
Support the assessment and proof-of-concept evaluation of AI platforms, LLMs, and agent frameworks for enterprise use.
Develop AI Agents & Workflows:
Build and enhance AI agents capable of supporting multi-step reasoning, automation, and task execution under established architectural patterns.
Engineer LLM Applications:
Design and implement LLM-based applications, including retrieval-augmented generation (RAG) pipelines, prompt engineering, and model optimization.
Integrate with Enterprise Platforms:
Contribute to embedding AI capabilities into OMS, CRM, loyalty, and digital platforms in partnership with engineering and product teams.
Apply AI Engineering Standards:
Follow established practices for AI model deployment, monitoring, safety, and compliance.
Cross-Functional Collaboration:
Work closely with Product, Digital Engineering, and Data Science teams to deliver AI-powered features and enhancements.
Responsible AI & Security:
Adhere to AI governance, privacy, and security controls when developing and deploying AI solutions.
Mentorship & Knowledge Sharing:
Provide informal mentorship to junior engineers and share best practices, while remaining primarily focused on hands-on delivery.
Qualifications Minimum Education and/or Experience:
Bachelor’s degree in Computer Science, Engineering, or a related field.
5+ years
of professional experience in software engineering, AI/ML, or data-driven platforms.
Additional knowledge and skills:
Hands-on experience building and deploying LLM-powered applications in production or near-production environments.
Working knowledge of RAG pipelines, embeddings, and vector search technologies.
Strong software engineering fundamentals and ability to deliver production-quality code.
Familiarity with responsible AI concepts, data privacy, and secure system design.
Exposure to regulated or operationally complex environments is a plus.
Tech Stack & Skill Requirements:
AI/ML Frameworks:
LangChain, LlamaIndex, Semantic Kernel, Hugging Face (or similar).
LLMs:
OpenAI GPT, Anthropic Claude, LLaMA, Falcon, or comparable models.
Vector Databases:
Pinecone, Weaviate, Redis Vector, Azure Cognitive Search.
Programming Languages:
Python (preferred); TypeScript/Node.js for integrations.
Security & Compliance:
Familiarity with OAuth 2.0, RBAC, and data privacy principles.
Security:
OAuth 2.0, RBAC, data privacy, compliance frameworks (GDPR, PCI).
#J-18808-Ljbffr
Responsibilities
Evaluate AI Technologies:
Support the assessment and proof-of-concept evaluation of AI platforms, LLMs, and agent frameworks for enterprise use.
Develop AI Agents & Workflows:
Build and enhance AI agents capable of supporting multi-step reasoning, automation, and task execution under established architectural patterns.
Engineer LLM Applications:
Design and implement LLM-based applications, including retrieval-augmented generation (RAG) pipelines, prompt engineering, and model optimization.
Integrate with Enterprise Platforms:
Contribute to embedding AI capabilities into OMS, CRM, loyalty, and digital platforms in partnership with engineering and product teams.
Apply AI Engineering Standards:
Follow established practices for AI model deployment, monitoring, safety, and compliance.
Cross-Functional Collaboration:
Work closely with Product, Digital Engineering, and Data Science teams to deliver AI-powered features and enhancements.
Responsible AI & Security:
Adhere to AI governance, privacy, and security controls when developing and deploying AI solutions.
Mentorship & Knowledge Sharing:
Provide informal mentorship to junior engineers and share best practices, while remaining primarily focused on hands-on delivery.
Qualifications Minimum Education and/or Experience:
Bachelor’s degree in Computer Science, Engineering, or a related field.
5+ years
of professional experience in software engineering, AI/ML, or data-driven platforms.
Additional knowledge and skills:
Hands-on experience building and deploying LLM-powered applications in production or near-production environments.
Working knowledge of RAG pipelines, embeddings, and vector search technologies.
Strong software engineering fundamentals and ability to deliver production-quality code.
Familiarity with responsible AI concepts, data privacy, and secure system design.
Exposure to regulated or operationally complex environments is a plus.
Tech Stack & Skill Requirements:
AI/ML Frameworks:
LangChain, LlamaIndex, Semantic Kernel, Hugging Face (or similar).
LLMs:
OpenAI GPT, Anthropic Claude, LLaMA, Falcon, or comparable models.
Vector Databases:
Pinecone, Weaviate, Redis Vector, Azure Cognitive Search.
Programming Languages:
Python (preferred); TypeScript/Node.js for integrations.
Security & Compliance:
Familiarity with OAuth 2.0, RBAC, and data privacy principles.
Security:
OAuth 2.0, RBAC, data privacy, compliance frameworks (GDPR, PCI).
#J-18808-Ljbffr