The UN Reform Resolution tasks UNDP to provide countries with an “integrator function” to accelerate progress towards the SDGs by tackling multiple interlinked and interdependent development challenges. The UNDP Global Policy Network (GPN) draws on expertise globally to provide more effective responses to the complex development challenges countries face in achieving the SDGs and responding to crisis in an integrated and coherent manner. Anchored in the Crisis Bureau (CB) and the Bureau for Policy and Programme Support (BPPS), the GPN has the responsibility for developing all relevant policy and guidance to support the results of UNDP’s Strategic Plan, which is aligned with the 2030 Agenda Sustainable Development Goals (SDG).

An SDG Integration Team located with UNDP’s Global Policy Network (GPN) offers a menu of services emphasizing direct short- to medium-term engagements to respond rapidly to requests from country offices for support on national implementation and monitoring of integrated policy solutions, qualitative and evidence-driven analysis for accelerated progress, and knowledge sharing and upscaling of innovative approaches to sustainable development. The team’s work emphasizes the application of evidence-driven data and analytics for SDG implementation and reporting.

In this regard, advances in digital technology are creating data at unprecedented levels of detail and speed, turning the stories of people’s lives into numbers every minute of every day, across the globe. An important focus of the integration work is to complement traditional data (e.g., national statistics,) with new and alternative sources including digital ‘breadcrumbs,’ satellite data, social media to identify emerging trends and gain new perspectives on issues in development.

Under the guidance of the Global Policy Advisor of the SDG Integration Bureau for Policy and Programme Support/Global Policy Network, the Data Science Consultant will lead on the development, training and testing of text analytics/Natural Language Processing (NLP) of reports, project information and other data for the organisation.

SCOPE OF WORK, RESPONSIBILITIES AND DESCRIPTION OF THE PROPOSED ANALYTICAL WORK

1. Build and deploy NLP/ML models for the SDG Integration Team’s work on SDG Acceleration Diagnostic, thematic taxonomy implementation and others as needed.
2. Design and implement data pipeline for NLP/ Machine Learning (ML) models
3. Research and experiment with NLP/ML methods for product Research and Development
4. Collaborate with IT and Thematic teams to discuss, design, test and implement text analytics approaches and enhancements

Expected outputs and deliverables:

Institutional Arrangements:

1. The consultant will work under the guidance and direct supervision of Global Policy Advisor of the SDG Integration Bureau for Policy and Programme Support/Global Policy Network and will be responsible for the fulfilment of the deliverables as specified above.
2. The Consultant will be given access to relevant information necessary for the execution of the tasks under this assignment.
3. The Consultant will be responsible for providing her/his own laptop. Given the global consultations to be undertaken during this assignment, the consultant is expected to be reasonably flexible with his/her availability for such consultations taking into consideration different time zones.

Duration of the work:

The consultancy is expected to last 4 months.

Duty Station:

This assignment will be home-based. 

Corporate Competencies:

• Demonstrates integrity by modeling the UN’s values and ethical standards.
• Promotes the vision, mission, and strategic goals of UNDP.
• Displays cultural, gender, religion, race, nationality and age sensitivity and adaptability.
• Treats all people fairly without favoritism.
• Fulfills all obligations to gender sensitivity and zero tolerance for sexual harassment.

Functional Competencies:

• Ability to carry out data exploration and analytics
• Able to communicate effectively in writing to a varied and broad audience in a concise and straightforward manner.
• Capable of working in a high- pressure environment with sharp and frequent deadlines, managing many tasks simultaneously.
• Excellent analytical and organizational skills
• Demonstrated ability to interact effectively with a diverse set of stakeholders.
• Works well in a team.
• Projects a positive image and is ready to take on a wide range of tasks.
• Focuses on results for the client.
• Welcomes constructive feedback.

Academic Qualifications:

• M.S. in Computer Science or relevant field, required.
• Field of study includes a focus on NLP or Machine Learning, desired.

Experience:

• Minimum 5 years of professional experience in data science with a focus on NLP or Machine Learning; required
• Minimum 5 years demonstrated experience with NLP/ML Entity Extraction, Topic Modeling, Text Classification; required
• Minimum 5 years’ experience with NLP/ML libraries (e.g. transformers, spacy, scikit-learn, rasa, SparkNLP); required
• Highly skilled in the use of Python; required
• Experience with other programing languages (e.g. Java, JavaScript); desired
• Experience with one of the Deep Learning Frameworks such as TensorFlow, Torch, MXNet, etc; desired
• Understanding of the fundamental of Transformer Models and experience of implementing one at the academic or industrial level; desired
• Previous experience working in the international development sector; desired

Language:

• Fluency in English, required
• Knowledge of another UN language considered an asset.

Application Procedure

The application package containing the following (to be uploaded as one file):

• A cover letter with a brief description of why the Offer considers her/himself the most suitable for the assignment.
• Personal CV or P11, indicating all past experience from similar projects and specifying the relevant assignment period (from/to), as well as the email and telephone contacts of at least three (3) professional references.
• 1-2 links to relevant NLP assignments

Note: The above documents need to be scanned in one file and uploaded to the online application as one document.

Shortlisted candidates (ONLY) will be requested to submit a Financial Proposal.

• The financial proposal shall specify a total lump sum amount, and payment terms around the specific and measurable deliverables of the TOR. Payments are based upon output, i.e. upon delivery of the services specified in the TOR, and deliverables accepted and certified by the technical manager. 
• The financial proposal must be all-inclusive and take into account various expenses that will be incurred during the contract, including: the daily professional fee; (excluding mission travel); living allowances at the duty station; communications, utilities and consumables; life, health and any other insurance; risks and inconveniences related to work under hardship and hazardous conditions (e.g., personal security needs, etc.), when applicable; and any other relevant expenses related to the performance of services under the contract.
• This consultancy is a home-based assignment, therefore, there is no envisaged travel cost to join duty station/repatriation travel. 
• In the case of unforeseeable travel requested by UNDP, payment of travel costs including tickets, lodging and terminal expenses should be agreed upon, between UNDP and Individual Consultant, prior to travel and will be reimbursed. In general, UNDP should not accept travel costs exceeding those of an economy class ticket. Should the IC wish to travel on a higher class he/she should do so using their own resources.
• If the Offeror is employed by an organization/company/institution, and he/she expects his/her employer to charge a management fee in the process of releasing him/her to UNDP under a Reimbursable Loan Agreement (RLA), the Offeror must indicate at this point, and ensure that all such costs are duly incorporated in the financial proposal submitted to UNDP.

The Financial Proposal is to be emailed as per the instruction in the separate email that will be sent to shortlisted candidates.

Evaluation process

Applicants are reviewed based on Required Skills and Experience stated above and based on the technical evaluation criteria outlined below.  Applicants will be evaluated based on cumulative scoring.  When using this weighted scoring method, the award of the contract will be made to the individual consultant whose offer has been evaluated and determined as:

• Being responsive/compliant/acceptable; and
• Having received the highest score out of a pre-determined set of weighted technical and financial criteria specific to the solicitation where technical criteria weighs 70% and Financial criteria/ Proposal weighs 30%.

Technical evaluation - Total 70% (70 points):

• Crtieria 1. Field of study includes a focus on NLP or Machine Learning, desired. Max. 5 points.
• Criteria 2. Experience with other programing languages (e.g. Java, JavaScript). Max. 5 points.
• Criteria 3. Experience with one of the Deep Learning Frameworks such as TensorFlow, Torch, MXNet, etc. Max. 5 points
• Criteria 4. Understanding of the fundamental of Transformer Models and experience of implementing one at the academic or industrial level. Max. 5 points
• Criteria 5. Previous experience working in the international development sector. Max 5 points
• Criteria 6. Knowledge of another UN Language. Max 5 points
• Criteria 7. Relevance of samples provided. Max 10 points.
• Criteria 8. Interview. Max 30 points

The top four candidates obtaining a minimum of 70% (28 points) of the maximum obtainable points for Criteria 1-7 will be invited for the interview. Please note that only shortlisted candidates will be contacted.

Only those candidates who obtain 21 points or more in the interview will be considered for financial evaluation.

Financial evaluation - Total 30% (30 points)

The following formula will be used to evaluate financial proposal:

p = y (µ/z), where

p = points for the financial proposal being evaluated

y = maximum number of points for the financial proposal

µ = price of the lowest priced proposal

z = price of the proposal being evaluated

Contract Award

The candidate obtaining the highest combined scores in the combined score of Technical and Financial evaluation will be considered technically qualified and will be offered to enter into contract with UNDP.

Payment modality

Payments are based upon output, i.e. upon delivery of the services specified above and deliverables accepted and upon certification of satisfactory completion by the manager. 

Annexes (click on the hyperlink to access the documents):

Annex 1 - UNDP P-11 Form for ICs

Annex 2 - IC Contract Template

Annex 3 – IC General Terms and Conditions

Annex 4 – RLA Template

Any request for clarification must be sent by email to cpu.bids@undp.org 

The UNDP Central Procurement Unit will respond by email and will send written copies of the response, including an explanation of the query without identifying the source of inquiry, to all applicants.