C
AI

Interns - Natural Language Processing: Agentic Document Understanding

Conxai Technologies GmbH · München, BY, DE

Actively hiring Posted 5 months ago

CONXAI's AI platform analyzes construction data to deliver insights and automate workflows. Our No-Code Agentic AI helps construction firms improve project control and prevent knowledge loss.

Tasks

We are looking for full-time interns (for min. 6 months) to solve cutting-edge machine learning problems and be a part of our product development. You should have experience in implementing large language models (LLMs) or Vision Language Models (VLMs) in PyTorch and frameworks like LangChain, LangGraph, LlamaIndex, etc. Prior experience in document understanding, information extraction, OCR, Retrieval Augmented Generation (RAG) with LLMs would be preferred.

  • Extract, pre-process data and from transactional documents of varying sizes, layouts and complexity.
  • Design and implement the automation of user workflows via an interactive user interface that leverages AI agents.
  • Collaborate with ML engineers on model design, experimentation and implementation
  • Collaborate with ML engineers to design a system with state-of-the-art ML components that effectively addresses customer KPIs
  • Discuss requirements with customer-facing members to understand the problem and its constraints
  • Proactively propose and implement iterative improvements
  • Propose and implement metrics to evaluate relevant KPIs
  • Integrate the solutions to a common codebase and demonstrate good software engineering practices
  • Communicate results and analysis on regular basis

Requirements

  • Pursuing a PhD / Master's degree in Computer Science or a related field enrolled in a tier-1 German or EU university
  • Experience in implementing machine learning models in PyTorch, specifically Large Language Models
  • Experience with document understanding
  • Experience with Large Language Models (LLMs) Retrieval Augmented Generation (RAG)
  • Experience with frameworks such as LangChain, LangGraph, LLamaIndex, etc.
  • Experience with OCR methods, OCR-free document understanding methods, e.g., Visual Document Question Answering (visual doc-QA) and Information Extraction
  • Proficient in Python and good software engineering skills
  • Good communication and interpersonal skills
  • Ability to work in a team-oriented environment
  • Strong problem-solving skills
  • Fluent in English
  • Eligible to work in Germany

Benefits

You will be a part of an inclusive start-up culture in a stimulating "work hard, play hard" environment. You will work with (and party with) great colleagues with diverse backgrounds. Team events and after-work activities are frequent at CONXAI. You will be empowered to bring new perspectives and create impact.

**This is a paid internship (EUR 2.100 gross per month) for a minimum of 6-months, based in Munich.

Applications for "Remote work" will not be accepted.

Tags & focus areas

Used for matching and alerts on DevFound
Fulltime Remote Ai Machine Learning Nlp Pytorch Generative Ai
Common Questions

Frequently asked questions

Quick answers about how DevFound's AI matching, resumes, and referrals work.

DevFound's AI Copilot ingests your profile, goals, and live job data to deliver curated matches in seconds. Every match includes a resume variant, suggested referrals, and interview prep so you can act immediately. The more feedback you provide, the sharper the Copilot becomes.

AI-led job searches shrink the hours spent sifting through boards and formatting resumes. DevFound pairs automation with your personal outreach, so you reserve energy for interviews and negotiation. Traditional networking still matters, but AI gives you a lift before you even send a message.

Modern AI roles expect comfort with production-grade code, data fluency, and practical ML tooling. The strongest candidates pair deep technical chops with storytelling—translating model impact to product, GTM, and exec partners. Continuous learning keeps you ahead as stacks evolve.

DevFound rewards active seekers. Keep your profile fresh, respond to match quality prompts, and enable alerts so you never miss a role. The AI prioritizes companies and teams that align with your feedback, accelerating both introductions and interview invites.

High-density tech hubs continue to host the deepest AI talent pools, yet distributed teams are catching up fast. Use DevFound filters to hone in on onsite, hybrid, or fully remote roles and watch openings expand across time zones.

DevFound aggregates thousands of remote AI openings and flags the nuances—core hours, async culture, and visa needs—up front. The Copilot also recommends how to position your distributed work experience so hiring managers know you can thrive on a remote team.