AI Engineer and Data Specialist

Key Responsibilities

• Design, build, and optimize LLM pipelines including retrieval, context assembly, grounding, prompting, and tool-calling.
• Develop RAG systems using vector databases, metadata design, chunking strategies, and hybrid retrieval approaches.
• Build agentic workflows and function-calling systems capable of reasoning, planning, and executing tasks.
• Evaluate model performance using structured test suites, synthetic QA generation, and benchmark datasets.
• Work closely with product and domain experts to translate ambiguous requirements into clear, structured LLM tasks.
• Diagnose and mitigate failure modes such as hallucinations, retrieval misses, and context collisions.
• Apply lightweight fine-tuning or LoRA when needed for task-specific improvements.
• Develop and maintain backend components for LLM pipelines (FastAPI, event systems, queues).
• Prepare unstructured documents (PDFs, HTML, logs, knowledge bases) for ingestion and indexing in vector/RAG systems.
• Support deployment across cloud or on-prem infrastructure (vLLM, TGI, Ollama, GPUs, token-budgeting).
• Ensure all AI features are grounded, safe, testable, reproducible, versioned, and backed by real evaluation—not guesswork.

Requirements

Required

• Bachelor’s d