Senior AI Application Engineer

Senior AI Application Engineer

The Senior AI Application Engineer will design, build, and scale advanced AI systems that transform how organizations solve complex business challenges. This role focuses on developing Retrieval-Augmented Generation (RAG) pipelines, agentic AI capabilities, and intelligent workflows powered by large language models. You will play a key role in turning emerging AI technologies into reliable, production-ready solutions that create measurable business value. The position combines hands-on engineering, architectural ownership, and strategic collaboration with business and technology leaders. You will help define AI roadmaps, identify high-impact use cases, and build scalable frameworks that accelerate future innovation. This is an opportunity for an experienced AI engineer to shape enterprise AI adoption in a collaborative, distributed, and technology-driven environment.

Accountabilities:

The Senior AI Application Engineer will own the development and evolution of AI-powered applications, focusing on RAG systems, agentic workflows, integrations, and scalable AI capabilities.

• Design, build, and maintain end-to-end Retrieval-Augmented Generation (RAG) pipelines, from data ingestion through response generation.
• Develop and optimize search and retrieval strategies, including indexing, schema design, hybrid search, vector search, filtering, reranking, and relevance improvements.
• Create effective chunking, metadata, and context strategies to improve retrieval accuracy and response quality.
• Build prompt orchestration frameworks, including dynamic prompt generation, context injection, and grounding mechanisms.
• Ensure AI-generated outputs are traceable, reliable, and supported by strong citation and verification approaches.
• Design and implement AI agents capable of tool usage, planning, multi-step execution, and integration with business systems.
• Connect AI agents with internal and external platforms, APIs, databases, and enterprise applications to enable real-world workflows.
• Develop evaluation frameworks to measure AI system performance, retrieval quality, response accuracy, and agent effectiveness.
• Establish guardrails and safety practices to reduce hallucinations, improve compliance, and ensure responsible AI behavior.
• Partner with product, data, and engineering teams to integrate AI capabilities into applications and operational processes.
• Collaborate with leadership to identify, prioritize, and deliver high-value AI use cases across the organization.
• Translate business challenges into practical AI solutions by defining requirements, data needs, technical approaches, and delivery plans.
• Create reusable AI development patterns, tools, and frameworks that accelerate future innovation.
• Contribute to AI governance practices and responsible AI adoption initiatives.

Requirements:

The ideal candidate is an experienced AI engineer with strong expertise in building production-grade generative AI systems, retrieval architectures, and intelligent automation solutions.

• Proven experience designing, building, or maintaining production RAG systems.
• Strong understanding of information retrieval concepts, including ranking, relevance, recall/precision tradeoffs, and search optimization.
• Hands-on experience with LLMs, embeddings, vector databases, and generative AI application development.
• Experience with hybrid search technologies such as Azure AI Search, Elasticsearch, or similar platforms.
• Experience designing and deploying AI agents and agentic workflows involving tool use, planning, orchestration, and multi-step reasoning.
• Experience integrating AI systems with enterprise applications such as CRM, ERP, ticketing platforms, APIs, or other operational tools.
• Knowledge of evaluation methodologies for generative AI systems, including retrieval evaluation and LLM-based assessment approaches.
• Experience with prompt engineering, LLM orchestration frameworks, and AI application architecture.
• Ability to optimize AI systems for scalability, reliability, latency, and cost efficiency.
• Experience designing guardrails and evaluation systems to improve AI safety and performance.
• Strong ability to translate ambiguous business needs into practical technical solutions.
• Experience building maintainable, scalable architectures integrated into core products.
• Ability to balance experimentation with production reliability and business impact.
• Self-motivated mindset with strong ownership, collaboration, and problem-solving skills.
• Must have current and ongoing authorization to work in the United States without restrictions or expiration.

Benefits:

• Competitive compensation package based on experience and qualifications.
• Remote and distributed work environment.
• Opportunity to build advanced AI products and influence enterprise AI strategy.
• Collaborative culture focused on innovation, technical excellence, and professional growth.
• Opportunity to work on impactful AI initiatives connecting technology with real-world business outcomes.
• Supportive environment that encourages ownership, creativity, and continuous learning.
• Access to professional development opportunities.
• Strong focus on work-life balance and employee growth.