AI Application Engineer

Role Mission

Own the translation of business problems into production-ready LLM applications. This role designs the application logic around the model: prompt architecture, context management, tool calling, RAG workflows, structured outputs, evaluation loops, and user-facing behaviour.

Core Responsibilities

. Build AI applications such as knowledge assistants, document analyzers, email/thread analyzers, recruiting assistants, workflow copilots, and operational decision-support tools.

. Design prompt systems, model instructions, retrieval flows, tool calls, conversation memory, and structured output schemas.

. Integrate cloud and local LLM APIs, OpenAI-compatible endpoints, embedding models, vision models, and rerankers.

. Create reusable AI workflow patterns for summarization, extraction, classification, reasoning support, report generation, and human review.

. Implement guardrails for reliability, source attribution, schema validation,fallback behaviour, and user confirmation before high-impact actions.

. Build evaluation sets and scoring methods to measure answer quality,hallucination risk, retrieval relevance, latency, and cost.

. Work with business users to turn vague automation ideas into specific AI product flows with measurable acceptance criteria.

Required Qualifications

. Strong Python or TypeScript development skills.

. Hands-on experience building with LLM APIs, chat completions, structuredoutputs, function/tool calling, or agent workflows.

. Practical understanding of prompt design, context windows, token limits, retrieval augmentation, and output validation.

. Ability to ship usable applications, not only prototypes or notebooks.

. Comfortable debugging model behaviour and separating application bugs from model limitations.

Nice-to-Have Experience

. Experience with LangChain, LlamaIndex, Semantic Kernel, instructor, Pydantic, or similar frameworks.

. Experience with multimodal applications involving images, OCR, audio, or document understanding.

. Experience with enterprise knowledge assistants, HR tools, operations automation, customer support, or internal productivity software.

. Familiarity with local LLM deployment tools such as Ollama, LM Studio, vLLM, TGI, or llama.cp