Description

Requirements

3 or more years of experience in software engineering, applied artificial intelligence, and LLM application development.

Proficiency in advanced prompt engineering techniques, Claude Desktop, and Model Context Protocol (MCP) server tooling.

Experience with designing Retrieval-Augmented Generation (RAG) pipelines and vector databases such as Pinecone or pgvector.

Experience in building evaluation harnesses, pipeline automations, and scripting utilizing Python or JavaScript.

Experience with adversarial prompt testing, jailbreak resistance, PII guardrails, and AI safety evaluation frameworks.

Experience in Intelligent Document Processing (IDP), OCR extraction tools like AWS Textract, and enterprise WMS or EDI data.

Excellent verbal and written communication skills.

Responsibilities

Architect and deploy enterprise RAG pipelines connecting warehouse management, EDI logs, and document repositories.

Establish and maintain a comprehensive prompt library utilizing chain-of-thought, few-shot, and XML-structured techniques.

Build custom AI integrations using Claude Desktop, Model Context Protocol (MCP) servers, and local file parsing tools.

Construct automated evaluation harnesses and benchmarking suites to measure prompt quality, latency, and cost.

Implement security guardrails to mitigate prompt injection, data leakage, and adversarial vulnerabilities in production workflows.

Deploy and tune LLM-powered applications including knowledge assistants, client-facing chatbots, and OCR data extractors.

Collaborate with cross-functional operations, legal, and product teams to translate business workflows into AI solutions

Key Skills

Education

Any Gradute