Work Location
Home-based (remote) or Bangkok, Thailand
Duties and Responsibilities
Org. Setting and Reporting The Environment and Development Division is seeking one intern for a minimum of four months (preferably six, the maximum internship duration) to support an internal automation platform that turns United Nations meeting media into structured, verified reporting and analytical outputs using local large-language-model inference. The internship is UNPAID and full-time. Interns work five days per week (35 hours) under the supervision of a staff member in the department or office to which they are assigned.
A fully remote (home-based) arrangement is possible, subject to approval. The intern will contribute to a mature Python codebase, working on test coverage, prompt and model evaluation, deterministic data-extraction tooling, and new-module scaffolding, all within an established architecture and coding standard. The intern will primarily support software quality assurance, structured model and prompt evaluation, and tooling development linked to ongoing automation initiatives. Daily responsibilities will depend on the individual's background and the internship period.
Duties may include, but are not limited to:
1. Author and extend automated tests (unit and mocked-LLM tests), lifting coverage across priority modules and hardening pure functions and data-extraction paths (30%)
2. Design and run structured model and prompt evaluations, such as per-language machine-translation selection and speech-recognition error detection, including building the labelled gold sets that make results measurable (25%)
3. Build and extend deterministic extraction tooling (pattern and catalog matching, fuzzy-match resolvers) consistent with the project's principle that language models never supply structured identifiers (25%)
4. Scaffold new modules and utilities to the house architecture, and improve documentation, refactoring and developer tooling (20%)
Qualifications/special skills
To qualify for an internship with the United Nations Internship Programme, applicants must, at the time of application, meet one of the following requirements:
(a) Be enrolled in, or have completed, a graduate school programme (second university degree or equivalent, or higher) related to computer science, data science, artificial intelligence, machine learning, computational linguistics, software engineering, or related disciplines; or
(b) Be enrolled in, or have completed, the final academic year of a first university degree programme (minimum bachelor's level or equivalent) related to computer science, data science, artificial intelligence, machine learning, computational linguistics, software engineering, or related disciplines. Special skills
(a) Strong Python proficiency, including experience with testing frameworks (pytest) and version control (git), is required.
(b) Foundational understanding of natural-language processing and of large-language-model prompting and evaluation is required.
(c) Familiarity with running or calling local LLMs (e.g. Ollama, Hugging Face) is an asset.
(d) Experience designing evaluation harnesses or working with structured (JSON) model outputs is an asset.
(e) Clean, documented and reproducible coding practice is essential, as contributions are made within an existing codebase and standard. Familiarity with the responsible use of AI tools to improve work quality and efficiency, in line with UN guidelines, is desirable.
Languages
English and French are the working languages of the United Nations Secretariat. Fluency in spoken and written English is required for the Internship Programme. Knowledge of another language used in Asia-Pacific is an asset (e.g. Chinese, Vietnamese, Bahasa Indonesia, Hindi, Urdu, Thai).
Intern Specific text
Interns are not financially remunerated by the United Nations. Costs and arrangements for travel, visas, accommodation and living expenses are the responsibility of interns or their sponsoring institutions. Interns who are not citizens or permanent residents of the country where the internship is undertaken, may be required to obtain the appropriate visa and work/employment authorization. Successful candidates should discuss their specific visa requirements before accepting the internship offer.