
Job Description – LLM / RAG Engineer
We are looking for a skilled LLM / RAG Engineer to design, build, and operate production-grade AI systems using large language models. The ideal candidate will have strong hands-on experience with RAG architectures, data preparation, evaluation, and LLMOps, along with the ability to deliver reliable and user-friendly conversational applications.
Key Responsibilities:
LLM Fundamentals
• Understand how LLMs generate text and common failure modes such as hallucinations and context limitations • Design effective prompts including system prompts, grounding techniques, and few-shot examples • Differentiate between embedding and generation models • Decide when to use RAG vs. fine-tuningRAG Architecture (Critical)
• Design and implement semantic and structure-aware chunking strategies • Build vector and hybrid search pipelines • Implement query rewriting, top-k selection, and re-ranking • Apply metadata filtering and enable citations for grounded responsesUnstructured Data Processing
• Extract text from PDFs, DOCX, HTML, and OCR sources • Perform data cleaning, deduplication, and normalization • Prepare chunk-ready datasets with rich metadataStructured Data & Analytics
• Strong SQL proficiency • Implement text-to-SQL workflows with guardrails • Enable schema-aware retrieval and analytical querying • Combine computed results with clear LLM-generated explanationsEvaluation & Monitoring
• Measure retrieval relevance and answer groundedness • Build offline evaluation datasets with human review • Monitor latency, cost, and response quality in productionLLMOps
• Manage prompt and model versioning • Support rollbacks and safe deployments • Track cost, performance, and system reliabilityFrontend & Conversational UX
• Design conversational experiences with follow-up handling • Implement citations and confidence indicators in responses • Build lightweight frontends using Flask • Capture and utilize user feedback for continuous improvementRequired Skills
• Strong understanding of LLM and RAG systems • Experience with vector databases and retrieval pipelines • Solid SQL and data handling expertise • Hands-on experience with Flask-based applications • Strong problem-solving, communication, and system design skills