AI Engineer

techcarrot; Abu Dhabi; On-site; AED 300,000 - 600,000; Full time

Job summary

techcarrot is seeking a hands-on AI Engineer in Abu Dhabi to design, build, and deploy production-grade GenAI and agentic AI solutions across enterprise data sources and platforms.

You will lead end-to-end development, from solution design to testing and production support, with strong emphasis on data validation, performance, and governance. Collaboration with offshore teams and secure Azure-based integrations are key components of the role.

Qualifications

• Strong hands-on understanding of LLMs, transformers, embeddings, prompt engineering, context engineering, RAG, and evaluation techniques.
• Experience building end-to-end GenAI and Agentic AI products from development through production deployment.
• Hands-on experience with LangChain, LangGraph, Haystack, n8n, and Microsoft Copilot ecosystem or similar frameworks.
• Practical experience designing multi-agent architectures and orchestrating reasoning, retrieval, tools, and actions.
• Strong experience with Vector and Graph Databases, including Azure AI Search, Neo4j, and Databricks Vector Search.
• Proven experience implementing RAG pipelines using structured and unstructured enterprise data.
• Strong experience with data validation, data-quality checks, reconciliation, KPI validation, and business-rule validation.
• Strong proficiency in Python, SQL, and Spark.
• Hands-on experience developing React / JavaScript / TypeScript applications.
• Experience developing APIs and backend services using FastAPI, Flask, or equivalent frameworks.
• Hands-on experience with PyTorch and/or TensorFlow.
• Experience working with large-scale AI/ML systems in production environments.
• Experience reviewing code and technical deliverables from distributed/offshore development teams.
• Strong problem-solving skills across AI, data, backend, frontend, and enterprise system integration.

Responsibilities

• Architect, build, and deploy production-grade GenAI and Agentic AI solutions across enterprise data sources and platforms.
• Implement Retrieval-Augmented Generation (RAG) pipelines with structured and unstructured data.
• Design hybridsearch architectures combining Vector DBs and Graph DBs for semantic retrieval.
• Develop multi-agent workflows with tooling, memory management, and orchestrations.
• Own end-to-end AI app development from AI/ML services to user-facing interfaces.
• Integrate React applications with enterprise APIs, data platforms, and authentication services.
• Build secure, scalable backend services using Python and relevant frameworks.
• Ensure enterprise requirements for performance, security, scalability, and governance.

Skills

LLMs & Transformers

LangChain / LangGraph / Haystack

Vector & Graph DBs

Python / SQL / Spark

React / JavaScript / TypeScript

APIs (FastAPI / Flask)

PyTorch / TensorFlow

GenAI / Agentic AI

Data validation & quality

Code reviews & offshore coordination

Tools

Azure App Services

Azure Functions

Bot Framework

Azure AI Search

Neo4j

Databricks Vector Search

Job description

Job description

• We are seeking a highly skilled and hands-on AI Engineer to design, build, and deliver enterprise-grade, production-ready AI, conversational AI, and agentic AI solutions that enhance how users interact with enterprise data, insights, recommendations, and business workflows.

• This is primarily a hands-on Individual Contributor (IC) role, with approximately 90% focus on individual technical contribution and 10% on coordinating and reviewing tasks delivered by the offshore development team.
• The role requires strong engineering capabilities across GenAI, AI/ML, data validation, backend development, and React application development, with end-to-end involvement from solution design and coding through testing, deployment, and production support.
• The role goes beyond traditional chatbots. You will architect and deliver multi-agent, tool-augmented GenAI solutions capable of reasoning, planning, contextual retrieval, and action execution across multiple enterprise data sources and platforms. You will work on secure, scalable, and governed AI systems aligned with enterprise architecture and compliance standards, ensuring data quality, reliability, explainability, observability, and continuous improvement.

GenAI & Agentic System Development

1. Design, develop, and deploy production-grade GenAI solutions using advanced LLMs such as OpenAI models.
2. Implement Retrieval-Augmented Generation (RAG) pipelines using structured and unstructured enterprise data.
3. Design hybridsearch architectures combining Vector DBs and Graph DBs (e.g., Azure AISearch, Neo4j) for semantic, contextual, and relationship-based retrieval.
4. Build AgenticAI workflows using frameworks such as LangChain, LangGraph, and Haystack, including:
   • Multi-agent orchestration (planner, retriever, evaluator, executor agents)
   • Tool-calling, function execution, and system-to-system automation
   • Memory management (short-term, long-term, and session-based)

Data Validation & Quality

• Perform end-to-end data validation before data is consumed by AI, ML, analytics, and decision-intelligence applications.
• Validate data completeness, accuracy, consistency, freshness, aggregations, calculations, and business-rule alignment across source systems and downstream applications.
• Work with business and data teams to validate KPIs, calculations, business rules, AI-generated insights, and recommendations before production release.
• Develop automated data-quality checks, validation frameworks, anomaly detection, and reconciliation processes.
• Identify data-quality issues and coordinate with Data Engineering and relevant teams for resolution.
• Ensure AI-generated insights and recommendations are based on validated and trusted enterprise data.

Full-Stack AI & React Application Development

• Take hands-on ownership of end-to-end AI application development, from AI/ML services and APIs through user-facing applications.
• Design and develop modern, responsive React-based web applications for AI, analytics, and decision-intelligence use cases.
• Build interactive interfaces for AI insights, recommendations, conversational experiences, dashboards, visualizations, and actionable workflows.
• Integrate React applications with AI/ML services, enterprise APIs, data platforms, authentication services, and backend systems.
• Develop scalable backend services and APIs using Python and relevant API frameworks.
• Ensure frontend and backend applications meet enterprise requirements for performance, security, scalability, usability, and maintainability.

Individual Contribution & Offshore Team Coordination

• Spend approximately 90% of the role as a hands-on Individual Contributor, directly involved in architecture, coding, development, debugging, testing, optimization, deployment, and production support.
• Allocate approximately 10% of the role to coordinating and reviewing technical tasks delivered by the offshore team.
• Review offshore team deliverables to ensure alignment with requirements, solution design, coding standards, and expected quality.
• Perform code reviews, technical reviews, and functional validation of assigned offshore deliverables.
• Provide clarification on technical requirements and tasks where required to support offshore delivery.
• Track assigned technical tasks and highlight dependencies, quality issues, or delivery risks.
• Work collaboratively with offshore AI Engineers, Data Engineers, Data Scientists, and Frontend Developers on integrated solution delivery.
• Remain directly accountable for assigned hands-on development activities while supporting the quality and integration of offshore deliverables.

Enterprise Integration &Cloud Engineering

1. Develop and integrate AI-powered chatbots and agents within the Azure ecosystem.
2. Integrate applications with enterprise identity and access-management frameworks including authentication, authorization, RBAC, and data-level security.
3. Build secure, scalable backend leveraging Azure App Services, Azure Functions, Bot Framework, Azure Cache for Redis, and related services.
4. Work closely with Cloud, Digital, Data Engineering, and Business teams for end-to-end solution delivery.

Production Readiness, MLOps& LLMOps

1. Implement guardrails for safety, hallucination control, data privacy, and responsible AI.
2. Monitor production performance across availability, latency, accuracy, reliability, and scalability.
3. Ensure enterprise-grade governance, including access control, auditability, and compliance with internal policies.
4. Apply MLOps / LLMOps best practices across the lifecycle:
   • Model / version management and prompt versioning
   • CI/CD pipelines for GenAI applications
   • Automated testing (prompt, retrieval, and regression testing)
   • Monitoring, logging, and observability for LLM outputs

Performance Optimization& Continuous Improvement

• Analyze AI application and agent performance using metrics such as accuracy, response quality, latency, adoption, and task completion.
• Optimize prompts, retrieval strategies, agent flows, APIs, database queries, and application performance based on actual usage.
• Identify and resolve performance bottlenecks across data, AI, backend, database, and frontend layers.
• Drive continuous improvement through experimentation, evaluation, monitoring, and user feedback.

Requirements

• Strong hands-on understanding of LLMs, transformers, embeddings, prompt engineering, context engineering, RAG, and evaluation techniques.
• Experience building end-to-end GenAI and Agentic AI products from development through production deployment.
• Hands-on experience with LangChain, LangGraph, Haystack, n8n, and Microsoft Copilot ecosystem or similar frameworks.
• Practical experience designing multi-agent architectures and orchestrating reasoning, retrieval, tools, and actions.
• Strong experience with Vector and Graph Databases, including Azure AI Search, Neo4j, and Databricks Vector Search.
• Proven experience implementing RAG pipelines using structured and unstructured enterprise data.
• Strong experience with data validation, data-quality checks, reconciliation, KPI validation, and business-rule validation.
• Strong proficiency in Python, SQL, and Spark.
• Hands-on experience developing React / JavaScript / TypeScript applications.
• Experience developing APIs and backend services using FastAPI, Flask, or equivalent frameworks.
• Hands-on experience with PyTorch and/or TensorFlow.
• Experience working with large-scale AI/ML systems in production environments.
• Experience reviewing code and technical deliverables from distributed/offshore development teams.
• Strong problem-solving skills across AI, data, backend, frontend, and enterprise system integration.