AI Architect / Engineer

Role Overview

We are seeking a hands-on, full-stack AI Engineer who thrives in fast iteration loops and

wants to design, build, and operate intelligent AI solutions at scale. You will work shoulder

to shoulder with cross-functional development teams to build GenAI and agentic AI

applications for enterprise use cases — from rapid proofs of concept (POCs) through MVPs

to scaled production deployments. Proven experience building and deploying AI products

is required; Travel and Hospitality experience is a plus.

LLM Application Engineering

• Own LLM application engineering as a core technical discipline, including

prompting, RAG, tool use, evaluation, guardrails, and orchestration — driving

iterative optimization in partnership with product teams.

• Build, fine-tune, and evaluate LLM-based applications for internal and customerfacing use cases, spanning retrieval-augmented generation, function calling, tool

use, multi-turn workflows, and guardrails.

• Design and implement agentic workflows where they add clear value — including

tool use, multi-step execution, and human-in-the-loop controls — with attention to

reliability, safety, and well-defined failure modes.

• Build robust agent capabilities including context engineering, memory and state

management (short-term and long-term), orchestration, routing, and tool integration

patterns.

• Build task-oriented AI agents and automation workflows with human-in-the-loop

controls, safety constraints, and full auditability.

• Design and implement pipelines for AI response enforcement, content safety, and

output formatting.

AI Platform & Solution Engineering

• Design and implement AI/ML solutions using Azure Machine Learning, Azure AI

Foundry (AI Studio), OpenAI on Azure — delivering resilient, observable, and costoptimized applications.

• Define the technical direction and long-term roadmap for internal AI platforms and

tooling; architect and lead full-stack AI application development across diverse

company use cases.

• Architect distributed systems to ensure high availability, low latency, and fault

tolerance; leverage Azure services to build cloud-native solutions.

• Build and maintain production-grade integrations connecting AI models with

internal tools, data sources, and enterprise workflows.

• Integrate AI into Power Platform solutions and line-of-business apps using tools and

services such as Copilot Studio, Azure Cognitive Services, and enterprise

connectors.

• Design context management patterns and integrate enterprise data sources such as

Fabric OneLake, Synapse, Microsoft Graph, etc

Data, ML & Model Engineering

• Execute training runs, ablations, evaluations, and model experiments; own model

codebases covering data loaders, training loops, evaluation harnesses, and

inference tooling.

• Optimize model performance across compute, memory, and distributed training

dimensions.

• Develop and maintain pipelines and ML models; implement robust feature

engineering and model monitoring across the full ML lifecycle.

• Build ML solutions end-to-end: data preparation, feature engineering, model

selection, training, validation and testing, and performance analysis.

• Partner with the Platform Engineer on dataset creation, feature and data contracts,

and pipelines.

• Create reproducible training and evaluation pipelines with versioning, experiment

tracking, robust validation, and clear documentation.

• Design and build advanced search, retrieval, and knowledge pipelines across

diverse data structures — including hybrid search, vector stores, graph databases,

and traditional data platforms.

• Define indexing strategies, metadata design, relevance tuning and reranking,

caching, freshness, access controls, and source attribution.

MLOps, DevOps & Production Delivery

• Write clean, testable, and maintainable code; ship AI services through the full SDLC

— build, test, deploy, monitor, and iterate.

• Implement MLOps and GenAIOps practices: CI/CD, reproducibility, environment

parity, and model, prompt, and agent versioning for operational readiness.

• Build CI/CD pipelines for models and prompts using Git, GitHub, and Azure

DevOps; manage environment provisioning, automated tests, A/B and canary

deployments, and rollbacks.

• Evolve production monitoring and regression testing for inference quality, cost, and

latency, driving iterative improvements post-release.

• Build evaluation and observability for GenAI and agentic systems: tracing and

instrumentation, regression test suites, automated scoring, and prompt and policy

optimization loops.

• Package models for production and collaborate with deployment engineers and

operations teams to iteratively improve performance.

Security, Governance & Responsible AI

• Enforce security best practices across the codebase and Azure infrastructure,

implementing defense-in-depth strategies and driving timely risk mitigation and

vulnerability remediation.

• Design for secure enterprise deployment: access controls, auditability, data

handling for sensitive and PII data, and responsible AI guardrails.

• Implement telemetry (App Insights, Prometheus, etc), responsible AI evaluations

(fairness, safety, toxicity), RBAC, data classification, and evidence trails aligned to IT

governance requirements.

• Define and oversee evaluation frameworks for AI-powered features, ensuring

inference quality, safety, and alignment with organizational standards.

Stakeholder Collaboration & Technical Leadership

• Partner with business stakeholders to translate product vision into technical and

data requirements for AI-powered solutions — advising on what is achievable, what

is risky, and what requires further investigation.

• Collaborate cross-functionally with frontend engineers, product managers, IT

infrastructure, security, and operations teams to align on technical solutions.

• Communicate clearly with technical and non-technical stakeholders; lead working

sessions, present recommendations, and write crisp technical documentation.

• Establish engineering best practices, design patterns, and quality standards for AI

systems development across the team.

• Mentor and guide engineers contributing to AI initiatives, fostering a culture of

technical excellence.

• Maintain hands-on involvement through prototyping, proofs of concept, and direct

contribution to critical implementations.

• Support proposal shaping and scoping: effort sizing, architecture options, risk

assessment, and delivery roadmaps.

• Create runbooks, model cards, data contracts, and playbooks; enable developers

and users on safe and effective AI use.

Innovation & Continuous Improvement

• Evaluate emerging technologies and drive adoption of best-in-class tools and

frameworks, incorporating their capabilities into the platform.

• Contribute to AI excellence by developing reference implementations,

documentation, and best practices, while tracking the evolving AI landscape and

identifying the right moments to introduce new capabilities.

• Build reusable components and accelerators — including templates, evaluation

harnesses, connectors, and orchestration patterns — that scale across multiple

product and client contexts.

• Drive code automation practices across the team to ensure maintainability and

extensibility.

• Rapidly iterate on AI tooling as the technology landscape and business needs evolve