> Markdown version of [/jobs/ext/4822141-genai-engineer-remote-role](https://www.wearedevelopers.com/jobs/ext/4822141-genai-engineer-remote-role). Every page supports `.md` or `Accept: text/markdown`. Links point to the HTML versions so they work for humans too. Agent guide: [/agents.md](https://www.wearedevelopers.com/agents.md). --- # GenAI Engineer Remote Role - **Company:** VERIDIANTECH LLC - **Location:** Jersey City, NJ, United States (Remote available) - **Experience:** Experienced - **Contract:** Permanent contract - **Skills:** JavaScript (Programming Language), Application Programming Interfaces (APIs), Artificial Intelligence, Continuous Integration, Data Integration, Python (Programming Language), Software Engineering, SQL Databases, TypeScript, Data Processing, LangChain, Retrieval-Augmented Generation, Large Language Models, Prompt Engineering, Llamaindex, Git, CrewAI, RAGAS (Retrieval Augmented Generation Assessment), DeepEval, Claude, Google Gemini, GPT, Promptfoo - **Published:** November 21, 2026 - **Apply:** https://www.dice.com/job-detail/283a73e8-e27e-45a0-8b69-ae05afa136fb ## About the Role MUST HAVE RECENT HEALTHCARE EXPERIENCE MUST HAVE PII/PHI UNDERSTANDING Candidates need to be able to develop use cases and solve hard problems. The Manager said he's going to be picky about selections since these are extremely important roles to fill, but he will provide us with good feedback but also needs to fill them quickly!, Ideally 8-10 years overall expereince, Typically 4+ years in software engineering with hands-on LLM application delivery. Has shipped AI features or agents using existing frameworks and services. ## Description * LLM application development: prompting and context engineering, function/tool calling, and building agents with LangChain, LlamaIndex, CrewAI or the Google ADK on top of an existing platform. * Retrieval-augmented generation: building RAG applications against a provided vector store and embedding service; chunking and retrieval tuning for a specific use case. * Model usage: calling models through a gateway or SDK (Gemini, GPT, Claude, open-weight models); prompt optimization and basic cost awareness per call. * Evaluation: writing and running evals for a specific application with RAGAS, DeepEval or Promptfoo; building test sets and interpreting quality and regression results. * Guardrails: applying provided guardrail and PII-handling policies to an application; recognizing prompt-injection and leakage risks. * Data and integration: Python, REST and SDK integration, SQL and data handling; connecting applications to APIs and data sources. * Delivery tooling: Git, CI/CD, notebooks, and AI-assisted development tools; building reporting and analytics outputs where needed. * Languages: strong Python; JavaScript or TypeScript useful for application surfaces.