Senior AI Engineer / Agentic AI Architect

CodeNinja is a global software and AI infrastructure company specializing in full-stack technology solutions across AI, software engineering, data, and digital transformation. Operating in Saudi Arabia and other global technology hubs, CodeNinja partners with organizations from various industries to drive business innovation and transformation. Our teams focus on AI, software engineering, data analytics, cloud, enterprise technology, and digital transformation initiatives.

We are seeking an experienced Senior AI Engineer / Agentic AI Architect to design, build, and deploy scalable, secure, and enterprise-grade AI solutions specifically for the banking and financial services sector. The role involves working extensively with Large Language Models (LLMs), Retrieval-Augmented Generation (RAG), and Agentic AI, delivering production-ready AI applications that emphasize observability, governance, and high performance.

Key Responsibilities
- Design and develop enterprise AI solutions using modern LLMs and Agentic AI frameworks.
- Architect multi-agent systems capable of planning, reasoning, tool integration, and workflow orchestration.
- Build production-ready RAG platforms that integrate structured and unstructured enterprise data.
- Develop scalable APIs and AI services primarily using Python and contemporary backend frameworks like FastAPI or Flask.
- Implement evaluation frameworks to assess LLM quality, safety, and performance.
- Optimize AI applications for latency, throughput, and infrastructure cost efficiency.
- Deploy and manage open-source LLMs in production environments.
- Collaborate with architects, product owners, business analysts, and DevOps teams to deliver enterprise AI platforms.
- Ensure compliance with enterprise security, governance, and responsible AI practices.
- Mentor engineering teams and contribute to AI best practices and reusable frameworks.

Required Qualifications
- 8 to 12+ years of software engineering experience, including at least 5 years of hands-on work in Artificial Intelligence, Machine Learning, and Generative AI.
- Strong expertise in machine learning, deep learning, NLP, transformer architectures, LLMs, and embedding models.
- Expert-level Python programming skills with experience in building production-grade backend systems, RESTful APIs, microservices, async programming, and scalable architectures.
- Proven experience designing and implementing Agentic AI solutions using tools such as LangGraph, CrewAI, OpenAI Agents SDK, AutoGen, Semantic Kernel, or LlamaIndex Workflows.
- Hands-on experience building enterprise RAG platforms with embedding models (OpenAI, Voyage AI, BGE, E5, Instructor, Cohere), vector databases (Pinecone, Qdrant, Milvus, Weaviate, ChromaDB), and graph databases (Neo4j, Amazon Neptune, Memgraph).
- Familiarity with search technologies including hybrid search, BM25, dense and sparse retrieval, semantic search, metadata filtering, re-ranking, and knowledge graph integration.
- Experience designing LLM evaluation frameworks using tools like Ragas, TruLens, DeepEval, OpenAI Evals, or LangSmith Evaluation, with knowledge of hallucination detection, faithfulness, relevancy, groundedness, toxicity, and regression testing.
- Expertise in AI guardrails and observability tools such as Guardrails AI, NeMo Guardrails, OpenAI Moderation, prompt injection detection, PII masking, LangSmith, Langfuse, Arize Phoenix, Weights & Biases, and MLflow.
- Skilled in prompt engineering techniques including Chain-of-Thought, ReAct, Tree of Thoughts, few-shot prompting, function calling, prompt optimization, and cost optimization.
- Experience deploying open-source LLMs (Llama, Mistral, Qwen, Gemma, DeepSeek) with inference engines like vLLM, TensorRT-LLM, Ollama, TGI, and SGLang, including GPU optimization, batch inference, autoscaling, multi-GPU deployment, and quantization methods.
- Proficient in MLOps and AI platform tools such as MLflow, Kubeflow, Docker, Kubernetes, GitHub Actions/GitLab CI, model versioning, experiment tracking, feature stores, continuous evaluation, and deployment.
- Experience with cloud AI platforms including Google Cloud Platform (Vertex AI), Microsoft Azure AI, AWS Bedrock, and OpenAI Azure.
- Knowledge of database technologies such as PostgreSQL, Oracle, MongoDB, Redis, and Elasticsearch/OpenSearch.
- Strong analytical, problem-solving, communication, and stakeholder management skills. Ability to lead technical discussions, architecture reviews, and mentor engineering teams. Comfortable working in Agile environments.

Preferred Qualifications and Benefits
- Experience in banking or financial services domains, including enterprise AI governance and responsible AI frameworks.
- Familiarity with regulatory environments such as SAMA or NCA.
- Experience building AI copilots, enterprise AI assistants, OCR, document intelligence, and intelligent automation solutions.
- Knowledge of integrating AI with BPM/workflow platforms like Appian, Camunda, or Pega.
- Bachelor’s degree in Computer Science, Artificial Intelligence, IT, Engineering, or related fields.
- Professional certifications such as Google Professional Machine Learning Engineer, Microsoft Azure AI Engineer Associate, AWS Certified Machine Learning Specialty, Databricks Machine Learning Professional, NVIDIA AI Certifications, or OpenAI/Anthropic ecosystem certifications are advantageous.

What We Offer
Competitive compensation aligned with experience and qualifications. Opportunities to work on large-scale technology and digital transformation projects within banking and financial services. Exposure to cutting-edge AI, data, and emerging technologies in a collaborative and technically driven environment. Professional growth and continuous learning opportunities alongside experienced technology and consulting professionals.

This description provides an overview of the role and is not exhaustive. CodeNinja reserves the right to modify responsibilities as needed.