CareerPlanGet AI match score →

LLM Engineer (GenAI, NYC)

💼 Full-time🗓 2026-06-24

Core

Build next-generation AI tools and agents that preserve critical thinking and enhance content integrity for educators, students, and writers.

Role type

Senior LLM Engineer (GenAI, Agentic Systems)

Builds

AI agents, multi-agent workflows, and prompt-optimized classification systems for content integrity.

Domain

Generative AI, Large Language Models, Information Integrity

Deliverable

production ML models

Required skills

Python, LLM frameworks (Langchain, LlamaIndex), agentic workflows, RAG, prompt engineering, exploratory data analysis, modular codebase architecture, experimentation tools

Preferred skills

open-source contributions, top-tier ML publications, early-stage startup experience, prompt optimization frameworks (DsPY, TextGrad)

Technologies

Python, Langchain, LlamaIndex, RAG, DsPY, TextGrad

Responsibilities

Fine-tune and evaluate state-of-the-art language models; optimize prompts for classification accuracy and style enforcement; develop multi-agent workflows using diverse data sources; iterate on AI agents using observability and experimentation tools; collaborate with product and design teams to build intuitive applications.

Seniority

Senior, hands-on IC

Rewrite
## About the role In this role, you'll build the next generation of AI tools that preserve and enhance critical thinking for humanity. The ideal candidate is someone who is adept at creating reliable AI agents, prompt engineering, possesses a great product sense, and is also an excellent software engineer. You'll be working on a fast-paced team of passionate builders to create industry-defining software that has attracted millions of users globally. ## What you'll contribute - Fine-tune and evaluate state-of-the-art language models - Optimize prompts to maximize classification accuracy, personalize outputs, and enforce style guidelines - Develop multi-agent workflows incorporating data from diverse sources using RAG - Improve and iterate on AI agents using observability and experimentation tools - Stay up-to-date with the latest literature and emerging technologies to solve novel problems - Work closely with product and design teams to develop intuitive applications that create societal impact ## Qualifications - 3+ YOE in Python - 1+ YOE in LLM framework like Langchain or LlamaIndex - 1+ YOE with agentic or RAG applications - Strong exploratory data analysis (EDA) skills to effectively leverage data in a way that informs pragmatic solutions - Experience pushing the cutting-edge in LLM abilities on novel tasks with subjective outputs - Excellent software engineer with experience building highly extensible and modular codebases, as well as complex pipelines - Self-starter (pitch, plan, and implement as a project owner in a fast-paced team) - Highly motivated to make positive societal impact - Ability to wear multiple hats and be a leader as our team grows - Visa for work in Canada or US ## Bonus - Strong open-source portfolio - Publications at top-tier ML venues - Experience working in an early-stage startup environment - Experience with a prompt optimization framework like DsPY or TextGrad ## About the company GPTZero is on a mission to restore trust and transparency on the internet. As the leading AI detection platform, we empower educators, students, journalists, marketers, and writers to navigate the evolving landscape of AI-generated content. With millions of users and institutions relying on us, we're building a category-defining company at the intersection of AI and information integrity. Our team comes from high-performing engineering cultures, including Meta, Perplexity, AWS, Affirm, and leading AI research labs, including Princeton, Caltech, and Vector Institute. At GPTZero, our recruiting team is involved in every step of the hiring process. We use AI-based tools (such as Endorsed.ai and Juicebox.ai) to help us to accelerate candidates at the resume review stage by marking when candidates met certain key criteria. These tools are never the final say in a hiring decision - humans are.
Sourced via wellfound · Listed on CareerPlan, which tracks 70,000+ jobs from 20+ sources.
Apply on Wellfound ↗