[Hiring] Android Developer Consultancy: In-App Plot Imaging for Ona @Alliance Bioversity & CIAT

Role Description

The Alliance of Bioversity International and CIAT seeks a senior Android developer for a 3-month consultancy. The goal is to capture a whole-plot image inside the Ona app, so breeders no longer switch to the phone's native camera.

Ona is a mobile and web digital phenotyping tool for on-station breeding teams in Sub-Saharan Africa. It runs at Alliance sites and with national partners such as TARI in Tanzania, Uganda, and Malawi. Breeders use an Android phone, often mounted on the Bruno physical aid, to image plots. Machine-learning models then extract traits such as plant stand, flower count, and pod count.

Objective

• Deliver a production-ready, in-app whole-plot capture feature in the Ona Android app.
• Specific objectives:
  • Assess and prototype at least three capture approaches and recommend one based on field evidence.
  • Build the chosen approach into the Ona app, linked to Ona's plot registration and metadata.
  • Validate it on target devices and in the field with Ona breeding teams.
  • Hand over clean, documented, maintainable code to the Ona team.

Scope of Work

The consultant will start open on method, test the options below, and commit to one by the end of month 1. The consultant may propose other options.

• Option A: In-app panorama, on-device stitching
  • Guided sweep in Ona's camera screen, stitched on the phone.
  • Main strengths: Works offline; instant result to check.
  • Main risks: Heavy on low-end phones; stitch errors from wind or uneven sweep.
• Option B: In-app guided multi-frame capture, cloud stitching
  • Ona captures overlapping frames; stitched on the server after sync.
  • Main strengths: Light on the phone; stronger stitching on the server.
  • Main risks: No result until sync; poor connectivity at field sites.
• Option C: Short video sweep
  • 3–5 s video of the plot; server extracts frames.
  • Main strengths: Fast and simple for the user.
  • Main risks: Large files; motion blur; needs a counting or tracking pipeline.
• Option D: Stitch-free counting
  • Overlapping frames counted one by one; duplicates removed by tracking.
  • Main strengths: Avoids stitching artefacts.
  • Main risks: Needs model and pipeline work with the Ona ML team.
• Option E: Single wide shot
  • Ultra-wide lens or a higher Bruno mount to fit the plot in one frame.
  • Main strengths: Simplest workflow.
  • Main risks: Not all phones have ultra-wide; distortion and lower detail at plot ends.

Technical Requirements

• No app switching; full capture happens inside Ona.
• Output covers the full ~4 m plot row at a usable resolution.
• Capture plus review takes no longer than today's panorama step, with a target of under 20 s per plot.
• Works on mid- and low-range Android phones.
• Capture works with no network; server steps run after sync.
• Works in bright sun, wind, and uneven terrain.
• User sees a clear guide during capture and a quality check after.
• Each image keeps plot ID, timestamp, device, and capture settings.
• Code follows Ona's Android architecture and standards.
• Third-party libraries must allow use in a publicly funded, non-commercial tool.

Deliverables and Timeline

• D1: Inception note: review of the current flow and earlier attempts, test plan, device list - Due Week 2
• D2: Options report with working prototypes, test results, and a recommended approach - Due Week 4
• D3: Beta build in the Ona app, ready for field testing - Due Week 9
• D4: Field validation report: capture time, success rate, image quality - Due Week 11
• D5: Final release merged into the Ona codebase, technical documentation - Due Week 12–13

Qualifications

• 5+ years of native Android development (Kotlin; Java a plus).
• Shipped at least one app with a custom camera feature using CameraX or Camera2.
• Hands-on image stitching, panorama, or computer-vision work.
• Use of phone sensors for capture guidance or motion tracking.
• Performance tuning on low- and mid-range Android phones.
• Offline-first apps and background sync.
• Fluent written and spoken English.

Desirable Qualifications

• Server-side image processing or video frame extraction.
• On-device ML or object tracking.
• Native code with the Android NDK.
• Experience in agriculture or apps used in Sub-Saharan Africa.
• Work on open-source or publicly funded projects.

Working Arrangements

• Reporting to the Head of Product, working daily with the Ona Android developers and ML team.
• Remote location.
• Weekly progress call; code reviewed through Ona's repository.
• Access to the codebase, test devices, and sample plot images provided by the Alliance.
• All code, documentation, and data produced belong to the Alliance.
• Consultant follows Alliance data-protection and data-sharing policies.

How to Apply

• Attach CV, highlighting Android camera, stitching, and computer-vision work.
• Include portfolio links: apps, repositories, or demo videos.
• Submit a financial proposal: daily rate and total fee for about 60 working days.

Shortlisted applicants will have a technical interview with the Ona team. Applications must include Ona in-app plot imaging consultancy as the position applied for. Applications closing date: 30 October 2026.