AI Engineer

LandEarly; United States; Remote; USD 120,000 - 180,000; Full time

Job summary

LandEarly is looking for an AI Engineer to build and improve AI-driven systems that power our auto-apply product — including resume and cover letter personalization, job matching, and the intelligent Q&A flows that surface candidate strengths.

You will design, build, and maintain AI/ML pipelines, refine prompting and retrieval, and optimize models for live job postings, with close collaboration across product and engineering to deploy features in the web app and browser extension, while

Qualifications

• Experience building and shipping AI/ML systems in production.
• Proficient in Python and backend API design.
• Hands-on with prompt engineering, embeddings, or fine-tuning.
• Ability to work with real-world text data and evaluation frameworks.

Responsibilities

• Design, build, and maintain AI/ML pipelines for resume tailoring, cover letter generation, and job-to-candidate matching.
• Develop and refine prompting, retrieval, and fine-tuning approaches for large language models used in production.
• Build systems to evaluate output quality, reduce hallucination, and ensure generated content reflects a candidate's real experience.
• Collaborate with product and engineering to integrate AI features into the web app and browser extension.
• Monitor, test, and improve model performance, latency, and cost in production.
• Work with data from live job postings and user profiles to improve matching and personalization accuracy.

Skills

Python

LLMs in production

API design

Backend services

Prompt engineering

Job description

LandEarly is looking for an AI Engineer to help build and improve the AI-driven systems that power our auto-apply product — including resume and cover letter personalization, job matching, and the intelligent question-and-answer flows that surface candidate strengths. You'll work on systems that process large volumes of live job postings and generate tailored, accurate application materials at scale.

What you'll do

• Design, build, and maintain AI/ML pipelines for resume tailoring, cover letter generation, and job-to-candidate matching
• Develop and refine prompting, retrieval, and fine-tuning approaches for large language models used in production
• Build systems to evaluate output quality, reduce hallucination, and ensure generated content reflects a candidate's real experience
• Collaborate with product and engineering to integrate AI features into the web app and browser extension
• Monitor, test, and improve model performance, latency, and cost in production
• Work with data from live job postings and user profiles to improve matching and personalization accuracy

What we're looking for

• Professional experience building and shipping AI/ML systems in production, ideally involving LLMs
• Strong software engineering skills in Python or a similar language, with experience designing APIs and backend services
• Practical experience with prompt engineering, embeddings, retrieval-augmented generation, or model fine-tuning
• Comfort working with ambiguous, real-world text data and building evaluation frameworks for generative output
• Experience with cloud infrastructure and deploying ML models at scale
• Strong communication skills and ability to collaborate closely with product and engineering teams

Nice to have

• Experience building consumer-facing AI products
• Familiarity with ATS platforms such as Greenhouse, Lever, Ashby, or Workable
• Experience with document parsing, resume/CV data extraction, or natural language generation for structured documents