freehire launches on Product Hunt on 26 August.

Follow →

Software Development Engineer

Summary

A junior Python engineer builds AI-powered document processing tools (PDFs) in a Dublin-based team, focusing on LLM-driven workflows, embeddings, and semantic search while learning from senior developers.

Junior Software Engineer (AI & Document Systems)
Location: Ireland (Hybrid — Dublin area)
Type: Full-time
About the role
Foxit is hiring a Junior Software Engineer to join our Ireland-based team building AI-powered, document-centric applications. This role is a strong fit for a recent graduate or early-career engineer with solid Python fundamentals and genuine curiosity about LLMs and document systems.
You’ll learn by doing—working alongside senior engineers to build and improve software that processes, manages, and analyses documents (especially PDFs) using modern AI techniques.
What you’ll do
Develop and maintain Python-based applications and services
Support delivery of AI-powered features using LLMs in document workflows
Assist with prompting and context management for document-focused use cases
Contribute to document ingestion and management workflows
Help process and extract information from PDF documents (text + structure basics)
Work with embeddings and introductory semantic search concepts
Write clean, tested, and well-documented code
Collaborate via code reviews, team discussions, and iterative delivery
Take direction from team leads and grow your skills through mentorship
What you’ll bring (required)
Bachelor’s degree in Computer Science / Software Engineering (or related)
Strong Python skills and good software fundamentals
Foundational understanding of AI and LLM concepts
Exposure to prompting and LLM-driven workflows (coursework, projects, internship, etc.)
Basic knowledge of document management concepts
Familiarity with PDF structure and text extraction concepts
Strong problem-solving mindset and willingness to learn quickly
Nice to have (bonus)
Introductory experience with RAG concepts
Familiarity with embeddings and/or vector databases
Exposure to vLLM, Ollama, or similar tooling
Basic understanding of REST APIs
Awareness of data privacy and GDPR principles
What success looks like
You ramp quickly on our codebase and ship reliable improvements
You collaborate well (communication, reviews, asking good questions)
You build confidence in LLM/document workflows while strengthening engineering fundamentals

What this application asks

lever

Resume/CV, Full name, Email, Phone, Current location, Current company, LinkedIn URL, Other website

  • What languages are you able to speak? written answer
  • What is your salary expectations? written answer
  • What is your notice period? written answer
  • What is the earliest you're able to start? written answer
  • Are you legally authorized to work in the location you are applying for without sponsorship? choose one · optional
  • Please briefly summarize your key experience relevant to this position: written answer
  • Tell me about the most impactful AI + document system you’ve built in production. What problem did it solve, what was the architecture (ingestion → retrieval/RAG → serving), and what did you personally own end-to-end? written answer
  • Walk me through a time your RAG/semantic search quality wasn’t good enough. How did you diagnose it (data, chunking, embeddings, prompts, evals), what changes did you make, and what measurable improvement did you see? written answer
  • Describe the hardest “PDF reality” problem you’ve dealt with. Messy layouts, tables, scans/OCR, metadata issues, multilingual docs—how did you handle extraction + structure, and what trade-offs did you make to keep it reliable at scale? written answer
  • Where are you currently based? choose one · optional

See also