Senior AI Engineer (LLMs, Generative AI) | Lead AI Engineer
Job Description:
We are looking for a Senior AI Engineer specializing in Large Language Models (LLMs) to lead end-to-end AI initiatives from discovery to production. You will own technical direction, collaborate with product and stakeholders, and build scalable LLM solutions (RAG, agents, fine-tuning, evaluation, and deployment). This role blends hands-on engineering with technical leadership and team mentorship.
Responsibilities:
· Lead LLM projects end-to-end: problem framing, solution design, implementation, rollout, and iteration.· Design and deliver LLM systems: retrieval-augmented generation (RAG), tool or function calling, agent workflows, prompt strategies, and guardrails.· Build production-ready services (APIs, workers, orchestration) for model inference and LLM applications.· Own architecture decisions: data flow, vector storage, caching, latency and cost tradeoffs, and reliability.· Create evaluation strategy: benchmarks, human review loops, regression testing, and monitoring.· Improve safety and quality: hallucination reduction, grounding and citations, policy filters, and PII handling.· Mentor engineers, set coding standards, review PRs, and raise overall team execution.· Communicate clearly with stakeholders: timelines, risks, tradeoffs, and measurable outcomes.
Required Qualifications (5+ years):
·5+ years of experience in software engineering, ML engineering, or applied AI with proven production delivery.· Strong Python skills and experience building backend services (Fast API or Flask, async jobs, queues).· Solid understanding of LLM concepts: token limits, context windows, prompting patterns, tool calling, retrieval and prompt engineering.· Hands-on experience with at least one of: RAG (vector databases), fine-tuning, or agents and orchestration (Lang Graph, Lang Chain, Llama Index).· Experience with MLOps fundamentals: CI or CD, monitoring, logging, versioning, and reproducibility.· Strong system design skills covering latency, cost, scaling, and security.· Ability to lead projects, drive execution, and coordinate across teams.2 / 2.
Preferred Qualifications:
· Experience delivering production systems on Open AI / Azure Open AI (embeddings + chat/function calling), with strong practices around reliability, prompt/version control, evaluation, monitoring, and spend governance.· Experience with LLM evaluation and QA processes.· Experience with cloud platforms (AWS, Azure, or GCP), Docker, and Kubernetes.· Experience building multilingual solutions (Arabic and English) when relevant.· Experience building advisory/consultant-style AI assistants for enterprise or government use cases, including guardrails, grounding, and human-in-the-loop workflows.
Tech Stack:
· Python, Fast API, Open AI API, database for chat history/metadata (Postgre SQL), and a vector store for retrieval (pgvector or managed vector DB)· Vector storage: pgvector, Pinecone, Weaviate, Chroma, or FAISS· Orchestration: Lang Chain, Lang Graph, Llama Index, or custom workflows· Observability: LLM tracing (Langfuse/Lang Smith) plus application monitoring/logging (Open Telemetry, centralized logs, dashboards).· Deployment: Docker, Kubernetes, Terraform· LLM providers: Open AI or Azure Open AI.
Additional Skills (Nice to Have):
· Familiarity with React (Vite-based projects), with the ability to collaborate effectively with frontend teams and understand UI-driven AI requirements.· Experience integrating AI services into full-stack applications, coordinating between frontend, backend, and AI layers.· Understanding of how AI outputs are consumed in user interfaces, including usability, clarity, and interaction flows.· Experience working in cross-functional product teams, translating business and user needs into AI-driven solutions.