AI Engineer

In this role, you will

work across both our Internal AI Automation and Customer-Facing AI teams , designing and deploying advanced AI-driven features and internal tools.
You ll be at the forefront of integrating Generative AI, LLM, and ML models into real products and workflows, using a modern AI tech stack that includes

LangChain ,

LlamaIndex ,

CrewAI ,

Anthropic (Claude), OpenAI (GPT-4 and others), AWS Bedrock , and the

Weaviate

vector database.
Your work will have a broad impact, from empowering our customers with intelligent product features to streamlining internal operations across various departments.
Some high-impact responsibilities you will be entrusted with:

Design, develop, and evaluate AI/LLM pipelines

for a variety of use cases from RAG-based knowledge assistants to multi-agent task automation.
This includes choosing the right components (LLMs, vector stores, prompt chaining, etc.) and ensuring they work together seamlessly.
Build robust evaluation and monitoring systems

to track model and pipeline performance over time.
You will define success metrics, implement automatic evaluations (for accuracy, relevance, latency, etc.), and use feedback to drive continuous improvements in our AI systems.
Collaborate with cross-functional domain experts (HR, insurance, sales, marketing, and others) to identify opportunities for AI automation and to gather requirements.
Develop and deploy autonomous AI agents

that can safely perform actions on our platform.
You will define agents roles, goals, and tool access, using frameworks like LangChain/CrewAI to coordinate complex sequences of actions.
Ensuring these agents are reliable and behave as intended will be a key part of your role (including rigorous testing in sandbox environments).
Optimize and integrate foundation models via APIs and AWS Bedrock .
You ll leverage large-scale models from OpenAI, Anthropic, and other providers (through AWS Bedrock s managed API or direct calls) and fine-tune or prompt-engineer them for our needs.
A big part of this is staying up-to-date on the latest models and figuring out which is best for a given task (accuracy vs.
speed, etc.).
Implement and maintain vector database integrations (Weaviate) for semantic search and retrieval.
You ll be responsible for how we index and query our unstructured data (documents, knowledge articles, etc.) so that our LLMs can fetch relevant context with minimal latency.
This includes crafting embeddings, setting up hybrid search (vector + keyword), and ensuring data privacy in the vector store.
Mentor and upskill team members in AI best practices .
You ll be a go-to expert for all things LLM.
Many of our engineers have strong software backgrounds but are newer to AI/ML you ll provide guidance through code reviews, knowledge-sharing sessions, and pairing, to raise the AI proficiency across the team.
Experiment, Innovate, and Lead :
Evaluate new tools, frameworks, and techniques in the fast-moving LLM ecosystem.
Whether it s a new prompt optimization approach, a better way to fine-tune a model, or an emerging open-source framework, you ll have the freedom to run proof-of-concepts and bring in innovations that keep Bayzat at the cutting edge.
You will also help guide strategic decisions on our AI roadmap, ensuring we invest in the highest-impact projects.
What you will need to have:


Hands-on LLM Experience :
Proven experience building applications powered by large language models (GPT-3.5/4, Claude, etc.).
You should be comfortable with prompt engineering, model tuning (via APIs or open-source models), and integrating LLMs into end-to-end systems.
Proficiency with Modern AI Frameworks :
Strong working knowledge of frameworks and libraries for building AI pipelines, such as LangChain, LlamaIndex, or similar.
Bonus if you have experience with agent orchestration frameworks like CrewAI for multi-agent systems.
Vector Databases & Retrieval Know-how :
Familiarity with vector search concepts and experience using a vector datastore (Weaviate, Pinecone, etc.) in an application.
You understand how to create embeddings and use similarity search to implement RAG ( retrieval-augmented generation)
Programming and Software Engineering Skills :
Fluent in Python (our primary language for AI work) and adept at writing clean, production-quality code.
Experience building APIs or microservices (we often wrap AI features behind APIs) is a plus.
Solid understanding of software engineering best practices (code reviews, testing, CI/CD).
Cloud and APIs :
Experience deploying or scaling AI solutions on cloud platforms.
Familiarity with AWS is a plus (we use services like AWS Bedrock and SageMaker for managed model hosting ).
Ability to work with RESTful APIs and build tools around them (for connecting AI agents to external services).
Analytical Mindset :
Ability to design experiments and analyze results critically.
You should be comfortable validating the effectiveness of an AI solution, whether through quantitative metrics or qualitative feedback, and debugging where things go wrong (e.g., why an agent took a bad step, or why a model gave a poor answer).
Collaboration & Communication :
Excellent communication skills with both technical and non-technical stakeholders.
You will be discussing ideas with software engineers one moment and explaining AI capabilities to a sales manager the next.
The ability to translate between AI jargon and layperson terms is important.
Disclaimer:
Naukrigulf.com is only a platform to bring jobseekers & employers together.
Applicants are advised to research the bonafides of the prospective employer independently.
We do NOT endorse any requests for money payments and strictly advice against sharing personal or bank related information.
We also recommend you visit Security Advice for more information.
If you suspect any fraud or malpractice, email us at ***
•