The UNDP Accelerator Labs Network is the largest learning network in the world. It includes 91 public innovation labs and a global curation team, all embedded within UNDP’s global architecture and country platforms.  

Each lab surfaces and reinforces locally sourced solutions to development challenges, and mobilizes a wide and dynamic range of partners who contribute knowledge, resources, and experience. The goal is to transform traditional development approaches by introducing new protocols, backed by evidence and practice, to accelerate the testing and dissemination of solutions within, and across countries, while at the same time enabling the global community to collectively learn from local knowledge and ingenuity at a speed and scale that our societies and planet require.

To support these learning outcomes, the UNDP Accelerator Labs global team is building a Network Learning Strategy and Prototype for knowledge management. The strategy has a strong digital component, that builds on the idea of “going where the information is”. The goal is to facilitate the detection of “where” knowledge is held in the network, and “why” it can be assumed to be held there, rather than trying to capture, infer, or extrapolate precisely “what” that knowledge is. This requires “listening” to the activities of the network, by centralizing and making sense of the content the labs put out, as well as the digital traces they leave behind as they conduct their work.

The Network Learning Prototype pulls together these unstructured data mainly text from various sources, including conversations on WhatsApp and Teams, blogs published on UNDP Country Office websites and Medium, and internal reporting feeds. While it is hardly big data, the volume is reaching a point where automation is becoming necessary to detect latent topics and trends that emerge from the network, and to structure and map open-ended taxonomies. The NLP researcher will work on this directly with the Lead Data Scientist of the UNDP Accelerator Labs global team.

The purpose of this procurement exercise is to contract an individual consultant who will work with the lead Data Scientist of the UNDP Accelerators Labs global team on a novel knowledge management pipeline that pulls together unstructured data (mainly text) from various sources including conversations on WhatsApp and Teams, blogs published on UNDP Country Office websites and Medium, and internal reporting feeds and computationally looks for latent topics and trends that emerge from the work being conducted across the network of Accelerator Labs. The main objective of the consultancy will be to improve the topic modeling component of the pipeline.

Duties and Responsibilities


  • Explore word and sequence embedding techniques to improve an early prototype for structuring open-ended, multi-language taxonomies.
  • Design, build, and evaluate topic models and more recent BERT-based zero-shot classifiers in Python for the Network Learning Prototype—primarily in English, but ideally also in French, Spanish, Portuguese, and Arabic.
  • Collaborate with different teams across UNDP to build a corpus of sustainable development-related documents, presumably in multiple languages, and fine-tune language models using this corpus.
  • Work with the Lead Data Scientist and the Full Stack Developer to take useful models and classifiers to production and integrate them into a suite of UNDP Accelerator Labs online tools and platforms.
  • Conduct occasional text analyses for the Accelerator Labs Network global team.
  • Document the work produced.

Expected outputs and deliverables:


Deliverables/ Outputs

Number of working days

Target Due Dates

% of payment


Fine tune language models to the corpora of Accelerator Labs documents


Apr. 2023



Build and maintain a latent feature space for classes (consistent, but unstructured tags used in certain datasets) to map diversity and cohesion of Accelerator Lab activities


Apr. 2023



Build topic models to feed into the Accelerator Labs Network Learning Strategy


July. 2023



Explore how zero-shot learning can improve the detection of emergent trends and patterns in the activities of the Accelerator Labs Network


Sept. 2023



Support ongoing activities related to NLP/ data science, both in the Accelerator Labs Global Team and across the network


Nov. 2023



Participate in general Accelerator Labs Global Team activities (participate in weekly team meeting, global drop-in calls, etc)


Nov. 2023



A.         Professionalism

  • Comfortable working with diverse programming languages, and open-source language models, frameworks, and libraries—including Python and PostgreSQL; BERT; SpaCy, scikit-learn, TensorFlow, PyTorch, or; Pandas and NumPY; and Matplotlib.
  • Passionate about natural language processing, data science, and their integration into digital products.
  • Passionate about open source/ free software movements.
  • Passionate about the use of data for human and social development.
  • Ability to work effectively as part of a team, but also independently with little supervision.
  • Ability and confidence to work directly with partners or clients to define requirements.
  • Ability to work with people from around the world, with different backgrounds, motivations, and competencies.

B.          Planning and organization

  • Ability to meet deadlines, work under pressure, manage workflows, and operate as part of a distributed team with members across almost every time-zone on the planet.
  • Ability to prioritize activities and assignments.
  • Possesses good organizational skills.

C.          Knowledge management and learnings

  • Motivation to continuously learn new things, and ability to put them to use.
  • Motivation to share personal knowledge and experience with others.

D.         Communication

  • Speaks and writes clearly and effectively, with a particular attention for the audience.
  • Demonstrates openness in sharing information.
  • Listens to others.

Required Skills and Experience

Academic qualifications:

  • Master's degree or higher in Computational Linguistics, Data Science, Computer Science, Information Retrieval, Statistics, Engineering, or any related field with strong computational and text analysis elements is required.


  1.  A minimum of three years of experience (this can include time as a PhD student) in building and training language models (e.g., recurrent neural networks, transformers, etc.) is required.
  2.  A minimum of two years of experience in using transformers and pre-trained language models, such as BERT, BART, or GPT; as well as NLP/ text analytics Python libraries, such as SpaCy, scikit-learn, TensorFlow, PyTorch, or is required.
  3.  A solid online portfolio or repository of NLP work that demonstrates the candidate’s experience is desirable
  4. A peer-reviewed paper track record (Academic publications) is desirable

In line with UNDP’s gender policy, female candidates are highly encouraged to apply.


  • Fluency in written and spoken English is required
  • Working knowledge of French is desirable
  • Working knowledge of Spanish, Arabic, or any other UN language is 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; and
  • A link to an online portfolio of similar work completed within the last three years, and a list of all relevant peer-reviewed publications

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):

  • Criteria 1: Relevance of the experience in building and training language models (e.g., neural networks, transformers, etc.). Weight =20%; Maximum points = 15  (3-5 years: 10 points, 5-10 years : 12.5 points, above 10 years: 15 points)
  • Criteria 2: Relevance of the experience in using transformers and pre-trained models, such as BERT, BART, or GPT; as well as NLP/ text analytics Python libraries, such as SpaCy, scikit-learn, TensorFlow, PyTorch, or Weight = 15%; Maximum points = 15 (2-4 years: 10 points, 4-6 years: 12.5 points above 6 years: 15 points)
  • Criteria 3: Relevance of the online portfolio or repository of work. Weight = 5%; Maximum points = 5 (no portfolio: 0 points, online portfolio that is not primarily NLP/ Data Science-related: 2.5 points, portfolio that is primarily NLP/ Data Science-related: 5 points)
  • Criteria 4: A peer-reviewed paper track record (academic publications). Weight = 10%; Maximum 10 points (less than 3 publications: 3 points; between 3 and 10 publications: 7 points; more than 10 publications: 10 points).
  • Criteria 3: Interview, Weight = 30%; Maximum points = 25

Having reviewed applications received, UNDP will invite the top three shortlisted candidates for interview. Please note that only shortlisted candidates will be contacted.

Candidates obtaining a minimum of 70% (49 points) of the maximum obtainable points for the technical criteria (70 points) shall be considered for the 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

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.

Institutional arrangement

The consultant will work under the guidance and direct supervision of Accelerator Labs Network Lead Data Scientist and will be responsible for the fulfilment of the activities and deliverables specified above.

The Consultant will be responsible for providing her/his own laptop.

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. 
  • The work week will be based on 35 hours, i.e. on a 7 hour working day, with core hours being between 9h00 and 18h00 daily.

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 

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.