AI Development Engineer - Onshore

Visa Status: GC/citizen.(C2C)

Location: Remote or NYC area; New York working-hour alignment preferred

Interparfums is advancing its AI transformation as part of this evolving how work gets done across the

business. The Senior Director of AI owns the strategy, roadmap, and organizational transformation. The

AI Engineer will be her hands-on technical partner who turns selected priorities into working

prototypes, practical initial implementations, and clear technical recommendations.

This role calls for an engineer with practical experience applying AI-native ways of working where they

fit. They look across built-in application features, enterprise copilots, configurable agents, and custom

builds to find the best-fit approach for the AI need. They test what works in practice, identify

overlapping capabilities, compare cost and effort, and apply their own judgment before recommending

or building anything. They work within IP’s policies, tools, and operating environment.

Priorities will be set collaboratively and may shift as technical discovery, platform capabilities, and

business needs evolve.

• Build and prototype: Develop AI agents, copilots, and proofs of concept selected by IP as

business priorities evolve. An initial focus is expected to be a chatbot embedded in a Microsoft BI

dashboard built on IP’s Microsoft data warehouse.

• Work AI-natively: Apply emerging AI-assisted and agentic approaches to research, solution

design, context and tool configuration, rapid prototyping, evaluation, testing, and documentation.

• Integrate enterprise data: Connect AI experiences to governed data, semantic models, and

business applications using the appropriate interfaces, including APIs, platform connectors, and

MCP-based tools or resources, in line with access controls and data ownership.

• Evaluate through evidence: Assess where IP applicable AI-enabled applications, MS Copilot,

OpenAI, Claude capabilities through research and hands-on testing. Identify overlapping applications

capabilities, compare cost and implementation effort, and communicate practical adopt, wait, or skip

recommendations.

• Engineer responsibly: Apply pragmatic evaluation, least-privilege access, human oversight,

observability, and token or credit cost controls appropriate to each prototype or initial

implementation.

• Work with IP teams: Work alongside IP developers and automation builders, adapting to

different levels of AI familiarity, limited team capacity, and IP’s current working practices.

• Transition ownership: Build production-oriented prototypes and selected initial implementations,

document key decisions, and prepare solutions for ongoing ownership by IP staff.

• AI-native working practices: Practical experience applying AI to parts of the engineering

lifecycle. Can point to specific ways AI has changed how they research, prototype, build, test,

evaluate, or document solutions. Be thoughtful on approaches for a business is at different stages of

AI adoption.

• Hands-on AI engineering: Experience configuring or building embedded AI features, LLM

enabled applications, copilots, agents, or comparable AI solutions, with the engineering judgment to

select an appropriate approach as requirements become clearer.

• Microsoft ecosystem experience: Hands-on familiarity with Microsoft’s enterprise AI and data

environment, along with sound judgment about technical fit.

• Data and integration fluency: Strong working knowledge of SQL, governed enterprise data,

APIs, and system integration. Able to reason about how conversational AI should interact with

trusted business data.

• Responsible implementation: Working knowledge of AI evaluation, data security, identity and

least-privilege access, prompt-injection risk, human review, and usage-cost fundamentals.

• Communication and collaboration: Able to explain technical options and write concise findings

Clearly,

• Additional AI platforms: Practical familiarity with OpenAI/ChatGPT and Anthropic/Claude

ecosystems.

• Microsoft data and applications: Experience with Power BI, semantic models, Microsoft Fabric,

Dynamics 365 Business Central, and Microsoft CRM for Sales.

• Emerging development practices: Exposure to agent development lifecycle concepts such as

evaluation-driven development, context and tool design, model or prompt versioning, observability,

and controlled rollout. Able to update IP on latest Microsoft AI evolutions, including agent delivery

architectures like the Copilot Super app.

• Proactively facilitates knowledge transfer to the IT staff within the scope of assigned projects

when requested, focusing on AI-augmented development workflows and modern AI ways of

working through co-engineering, peer pairing and walk-throughs of active project deliverables.

• Technical evaluation: Experience testing AI vendor claims, comparing implementation options, or

translating a proof of concept into an evidence-based recommendation.