Principal Engineer

Fulcrum DigitalMiami, FloridaOn-siteFull-timePrincipal, 12–15+ yearsListed 13 hours ago

Apply now

About this role

Who are we?

Fulcrum Digital is a global AI-first enterprise transformation company with over 25 years of experience. We partner with enterprises across financial services, insurance, healthcare, retail, manufacturing, higher education, and logistics to move from AI experimentation to scalable business outcomes. Fulcrum Digital works with over 100 global clients, including Fortune 500 enterprises, combining deep industry expertise with capabilities in enterprise AI, digital engineering, cloud modernisation, platform integration, and generative AI.

The Role

We’re looking for a Principal Engineer to be the on-ground technical authority for conversational AI across a major consumer travel and hospitality brand’s digital channels: the guest-facing assistant on mobile and web, ecommerce, and the contact center. This is a senior technical leadership role that stays close to the code. You will set the architecture, lead and grow multiple engineers across several initiatives at once, and be the person who explains technical direction, risk and progress to directors and VPs.

You will be involved end to end, from discovery and architecture through development, testing and go-live, on both the technical and the business side. We need someone who can debug a production issue in the morning, run a design review at noon, and brief a non-technical executive in the afternoon.

What you’ll do

- Own the architecture: Define the end-to-end architecture for the conversational AI platform across mobile, ecommerce web and contact center, make and document key technical decisions (build vs. buy, model selection and routing) with clear cost, latency, accuracy and security trade-offs, set engineering standards and reusable patterns adopted beyond your own team, and plan how the architecture evolves over time.
- Stay hands-on: Write production code, build reference implementations and proofs of concept, review code and designs, lead root-cause analysis of hard production issues, and design for failure at scale (retries, idempotency, graceful degradation, LLM cost control).
- Build great conversational experiences: Design dialog orchestration, intent handling, multi-turn context and RAG grounded in trusted sources, own fallback and low-confidence handling with seamless human escalation, establish how quality is measured in production, and build in responsible AI (hallucination control, grounding, prompt-injection defense, guest and payment data protection) from the start.
- Lead and grow engineers: Provide technical leadership to multiple engineers and teams across several initiatives, including engineers who don’t report to you, originate technical initiatives from idea to adoption, raise the bar through mentoring and review practices, and hold a defensible technical line with senior engineers and leadership.
- Partner with the business: Translate business goals into a technical roadmap with product, guest experience, contact center and security partners, explain complex AI concepts to non-technical directors and VPs, roll up technical status into clear updates for leadership, and reframe unsound requests into phased options that still deliver value.

Requirements

Requirements

- 12+ years of software engineering experience, with recent, hands-on coding in Python and at least one of Java, TypeScript/Node.js or Go
- 3+ years designing and shipping conversational AI, chatbot, virtual assistant or NLP systems to production at scale, including dialog state, intent handling and human escalation, not only LLM API calls
- Hands-on experience with LLM application patterns: RAG, embeddings and vector search, prompt and context engineering, agent or workflow orchestration (e.g., LangGraph or similar), and LLM evaluation
- Strong distributed systems background: microservices, REST APIs, event-driven architecture, and cloud-native deployment on AWS or a comparable cloud
- A track record of setting architecture across multiple teams, with decisions documented and adopted beyond your own team
- 3+ years leading engineers technically at a senior staff, lead or principal level, with concrete examples of growing other engineers
- Excellent communication: able to brief executives, run architecture reviews, and write clear design documents

Nice to have

- Experience integrating AI assistants with contact center platforms and omnichannel (voice and chat) journeys
- Experience with managed conversational platforms (e.g., Amazon Lex, Amazon Bedrock, Dialogflow CX, Azure AI / Copilot Studio) and knowing when to build custom instead
- Background in travel, hospitality, cruise or other high-volume consumer ecommerce
- Experience with mobile and web channel integration, identity providers (OAuth/OIDC), and PCI or PII-sensitive environments
- Observability tooling such as CloudWatch, X-Ray, Datadog or OpenTelemetry

What success looks like

- First 30 days: You understand the current platform, codebase and stakeholders, and have shipped or reviewed meaningful code.
- First 90 days: You have published a target architecture and the first key decision records, and teams are building toward them.
- Ongoing: Engineers across teams look to you for technical direction, leadership trusts your updates, and the assistant’s quality metrics are measured and improving release over release.