What is the project, and why should you care?

Our client is seeking a compact, senior engineering squad from a single vendor to build and evolve an AI‑powered, security‑first platform. The team will deliver new features, integrations, and a full English↔Hebrew (LTR↔RTL) experience. Tech stack: Frontend – Angular; Backend – .NET (C#) microservices; Cloud – Azure; CI/CD – Azure DevOps; Design – Figma; AI – Azure OpenAI / OSS models (as applicable), vector search (e.g., Azure AI Search/pgvector), orchestration (e.g., Semantic Kernel/LangChain), MCP for tool integrations.

You will be an excellent fit for this position if you have:

Tech Stack & Core Expertise:

• Backend: C#, .NET, Microservices architecture
• Cloud & DevOps: Azure, AKS (Kubernetes), Azure DevOps CI/CD, Infrastructure as Code
• AI/ML Development:
• Experience building and deploying offline models (non-SaaS / tenant-isolated AI instances)
• Strong background in RAG (Retrieval-Augmented Generation) pipelines, embedding creation, and index management
• Expertise in classification models, fine-tuning, and AI lifecycle automation
• Hands-on experience with MLflow, model versioning, and training pipelines
• Familiarity with vector databases, document ingestion, and data preprocessing for unstructured data
• Experience integrating AI models with microservices and APIs in production environments

Security & Compliance:

• Strong understanding of application security, data protection, and secure AI design principles
• Experience implementing role-based access, data isolation, and compliance frameworks (e.g., NIST, ISO, GDPR)

Preferred Soft Skills:

• Ability to lead cross-functional development between AI, backend, and DevOps teams
• Comfortable defining architecture, reviewing code, and mentoring engineers
• Strong documentation and communication skills

Here are some of the things you’ll be working on:

• Own the AI architecture and main components; lead the team; drive security, quality, and delivery.
• Define AI system architecture: model serving, retrieval (RAG), evaluation, guardrails, and data pipelines.
• Choose/operate model endpoints (Azure OpenAI or OSS), vector DB, caching, and orchestration framework.
• Establish AI safety (prompt‑injection defenses, PII redaction, rate‑limit/abuse protection, content filters).
• Lead MLOps (datasets, fine‑tuning/LoRA when needed, evals, versioning, rollback, drift monitoring).
• Own cross‑team engineering standards (coding, testing, docs, ADRs) and delivery plan.