AI Engineer / Applied AI Engineer

About this Role:

Smart Food Safe, a global Quality and Food Safety Management SaaS company, is looking for an AI Engineer with proven experience building and deploying AI capabilities within real software products.

We value demonstrated production AI experience over years of experience. We are looking for a hands-on engineer who can take AI solutions from concept → architecture → prototype → evaluation → production.

Technical Skills

• LLMs & Prompt Engineering: OpenAI/Azure OpenAI, Claude, Gemini; system/few-shot prompting, context engineering and optimization.
• Structured Outputs & Tool Calling: Schema-based outputs and function/tool calling with APIs, databases, and application services.
• Agentic AI: Multi-step workflows, state/tool orchestration and human-in-the-loop controls using LangGraph, LlamaIndex, Semantic Kernel, MCP, or equivalent.
• Advanced RAG: Document parsing, chunking, embeddings, vector databases, hybrid search, reranking, citations, grounding, and hallucination reduction.
• Document & Multimodal AI: OCR, PDFs, images, tables, document extraction, classification, and validation.
• Evals & Observability: LLM-as-a-judge, automated evaluation, regression testing and tracing using Promptfoo, DeepEval, LangSmith, Langfuse, or equivalent.
• Performance & Reliability: Model routing, caching, streaming/SSE, retries, fallback handling, rate-limit management, latency and cost optimization.
• Core Engineering: Expert Python, FastAPI, asyncio, REST APIs, SQL/NoSQL, MongoDB, Git, automated testing, Docker and CI/CD.
• Cloud & Security: Azure/AWS, AI services, scalable deployment, monitoring, prompt-injection protection, secure RAG, tenant isolation and data privacy.

Proven AI Expeirience - Required

Candidates must demonstrate at least two meaningful AI solutions they personally built, preferably deployed in production. You should be able to explain:

• End-to-end architecture and your personal contribution
• Models, frameworks and technologies selected
• How the AI was integrated into the core product
• RAG, agents, document AI or other AI techniques used
• How accuracy, hallucinations and reliability were measured
• Security and data privacy controls
• Production scale, latency and cost
• Technical challenges and how you solved them
• Measurable customer or business outcomes

Candidates should be prepared to demonstrate and technically defend their previous AI work during the interview.

What we are looking for:

A strong AI + software engineer who has shipped AI into real products, understands how to make AI accurate, secure, scalable, observable and cost-effective, and can independently take an AI use case from idea to production.

2–4+ years of relevant AI/ML/software engineering experience preferred. Proven production AI capability matters more than years of experience or academic credentials.

Application Requirement:

Submit your resume plus details of two AI solutions you personally built: Problem → Architecture → Your contribution → Technology → Evaluation/Accuracy → Production scale → Business outcome

GitHub, demos, architecture diagrams or other evidence of your work are strongly encouraged. We are looking for AI builders—not simply candidates familiar with AI terminology.