II

Research Technician - Yam Pollen Research

Iita

Full-time Ibadan, Oyo, NG
Posted 16 hours, 30 minutes ago 20 views 0 applications

Job Description

Here's a thinking process: 1. **Analyze User Input:** - User is acting as a job listing editor. - I receive raw scraped text from a job website. - Job is to extract ONLY actual job information, return clean, readable format. - Must REMOVE specific things: social sharing, author bylines, "you may also like", navigation, comments, ads, cookie notices, duplicate text, category labels, stray numbers/formatting artifacts. - Must KEEP and STRUCTURE: job title, company, location, description/responsibilities, requirements/qualifications, how to apply, salary, deadline, job ID/reference, contract type/level. - Return ONLY the cleaned job text. No commentary, headers like "Here is the cleaned version", or markdown formatting. Just the clean job listing text. Wait, the actual prompt I receive has TWO parts: - First part: "You are a job listing editor... Return ONLY the cleaned job text." - Second part: "You receive a plain-text job description. Your ONLY job is to format it as clean semantic HTML." with specific HTML rules. - Then it gives a job description text. I need to figure out which format to output. The very last instruction says: "Return ONLY the HTML. No markdown fences, no explanation, no preamble." And it gives rules for HTML formatting:

,

,
  • , no classes/styles/div/br, preserve ALL original content word-for-word, no summarizing, if no clear sections just wrap in

    . The first part says "Return ONLY the cleaned job text. Do not add any commentary... or markdown formatting. Just the clean job listing text." But then the second part overrides with HTML formatting rules. Let me read carefully. The user message starts with "You are a job listing editor..." then has "REMOVE all of the following..." and "KEEP and STRUCTURE:" and "Return ONLY the cleaned job text." Then it says "You receive a plain-text job description. Your ONLY job is to format it as clean semantic HTML." with rules about

    ,

    ,
    • , etc. And "Return ONLY the HTML. No markdown fences, no explanation, no preamble." Then it gives the job description text. I think the task is to take the provided job description text, clean it according to the rules (remove stuff, keep stuff), and output it as clean semantic HTML using the specified tags, preserving all original content word-for-word. Let's look at the job description text: ```

      The International Institute of Tropical Agriculture seeks suitable Nigeria nationals for the position below at the Institute’s Headquarters in Ibadan.

      Position:   Research Technician - Yam Pollen Research

      Contract:   6-month renewable contract                                

      Location: Ibadan

      Closing Date: 15 October 2026

      DUTIES

      ·       Field monitoring, pollen collection, and storage

      ·       Regularly monitor designated yam fields and crossing blocks for flowering.

      ·       Identify male plants and flowers at the appropriate developmental stage for pollen collection.

      ·       Collect mature anthers/pollen from designated yam genotypes.

      ·       Conduct pollen collection at the appropriate time of day, including early-morning collection when required.

      ·       Record genotype/accession, species, plot number, date, collection time, location, flower stage, and other required metadata.

      ·       Ensure that all samples are correctly labeled immediately after collection.

      ·       Transport samples from the field to the laboratory under the prescribed conditions.

      ·       Maintain daily records of flowering and pollen availability for designated genotypes.

      ·       Maintain traceability of each sample throughout processing.

      ``` Rules for cleaning: - REMOVE: Social sharing text, author bylines, "you may also like", navigation, comments, ads, cookie notices, duplicate text, category labels that aren't part of the job, stray numbers/formatting artifacts. - KEEP and STRUCTURE: Job title, company/organisation name, location, job description and responsibilities, requirements/qualifications, how to apply, salary, deadline/closing date, job ID/reference number, contract type/level. - HTML formatting: Use

      for intro paragraphs and general text. Use

      for section headers (Responsibilities, Qualifications, Requirements, Education, Experience, Skills, How to Apply, Key Duties, About the Role). Use
      • for list items. No CSS classes, inline styles,
        ,
        . Preserve ALL original content word-for-word. If no clear sections, just wrap paragraphs in

        . Return ONLY the HTML. No markdown fences, no explanation, no preamble. Now, I need to process the given text into HTML. Let's identify parts: - "The International Institute of Tropical Agriculture seeks suitable Nigeria nationals for the position below at the Institute’s Headquarters in Ibadan." -> This is an introductory paragraph. Keep as

        . - "

        " - empty paragraphs. Probably should remove or handle. Rule says "If text has no clear sections, just wrap paragraphs in

        tags". But empty paragraphs might be artifacts. I'll likely need to omit empty

        or treat them as whitespace. The rule says preserve ALL original content word-for-word. But empty tags aren't content. I think I should remove empty paragraphs since they're not content, but the rule says preserve all original content word-for-word. Hmm. Maybe keep them as

        ? But the HTML rules say no
        , and

        is technically allowed but maybe not needed. I'll see. - "Position:   Research Technician - Yam Pollen Research" -> Job title. Should be kept. The "Position:" might be considered a header or part of the title. I'll keep it as text. Could wrap in

        or

        . Since it's a label, maybe keep as paragraph text. - "Contract:   6-month renewable contract" -> Contract type/level. Keep. - "Location: Ibadan" -> Location. Keep. - "Closing Date: 15 October 2026" -> Deadline. Keep. - "DUTIES" -> Section header. Should become

        DUTIES

        or maybe

        Key Duties

        . Rule says use

        for section headers (e.g. Responsibilities, Qualifications, Requirements, Education, Experience, Skills, How to Apply, Key Duties, About the Role). So "DUTIES" maps to "Key Duties". I'll use

        Key Duties

        or just

        DUTIES

        . To be safe, I'll use

        DUTIES

        since it says "e.g." and I should preserve content word-for-word. But the header text should match the section. I'll output

        DUTIES

        . - The list items under DUTIES: each starts with "·      ". These are bullet points. Rule says use

MJC
ECHO
Your MJC Assistant

I'm ECHO, your MJC career assistant. I can help you find jobs, explore career tools, and connect with opportunities across Africa.

How was your experience with ECHO?