Embedded with the Cough against Covid team

Documenting the journey of one partner volunteer as she recorded coughs.
The focus of the study was to determine if the cough sound has Covid-19 signatures.

Mangal is in her early 20s. A few months ago, when the pandemic struck, she was pursuing a postgraduate course in respiratory therapy in Pune, a city close to Mumbai. The college where she was studying closed due to the lockdown. She wanted to pursue an internship but her professors advised against it. “Go home,” they said. Mangal could have done exactly that. She could have gone east and taken an overnight train home to Belgaum, a city on the border of Maharashtra and Karnataka. But she didn’t. She went west. She went to Mumbai. While the country was locking down, she was told about a volunteering opportunity in Mumbai with a not-for-profit called Doctors For You (DFY). She was asked if she would help in participating in a cough study, which was being run by Wadhwani Institute for Artificial Intelligence (Wadhwani AI). The focus of the study was to determine if the cough sound has Covid-19 signatures. If it did, it would help in triaging potential patients faster. It caught her interest and despite the restrictions, she made it to Mumbai. 

In Mumbai, Wadhwani AI and DFY embedded her in an isolation centre. “My first job was to shadow doctors and nurses during the rounds,” she says. This was an important part of the routine. While she did the rounds, she established a rapport with the patients. As time went by, she started to check in on patients, asking them if they ate, if they were given their medications. She even started assisting the hospital staff with intake and the nurses in simple non-medical tasks. What helped was that she had worked in neonatal care before and was used to being around an active contagion. Sometimes she would even suggest different medication to doctors and nurses. 

Working in a Covid ward, however, did scare her sometimes. “Yes, you’re always a little afraid but we were given good PPEs. Also, as soon as I started working there my experience kicked in and I settled down quick,” she says. There were a few scares when she would develop headaches. “I have frequent migraines, so every time I got one, I took some time off,” Mangal says. She got tested a few times as well. She returned negative tests every single time. 

While the doctors, nurses and the patients got used to having her around, DFY and Wadhwani AI were trying to get ethical committee approvals to conduct the study. This was also an important period for Mangal because she was getting used to wearing PPEs almost all throughout the day. She also played another role. She was observing the way the isolation centres were being run and helping program managers at Wadhwani AI set up processes

Recording the coughs

As soon as the approvals came in, Mangal sprung into action. “I would meet the patients after lunch and chat with them about how they were feeling,” she says. After lunch was an important time. The isolation centres were huge and sometimes resources were stretched. Because all patients were kept in isolation, they got lonely. “They liked it when someone came to speak to them,” she says. She would talk to them about Cough against Covid. “I told them that in cities like Mumbai and Delhi, tests were easily available but the virus is spreading into rural areas. Tests there are difficult,” she says. And then she delivered the clincher. “Your cough could save the lives of thousands of people,” she would tell them.

Once the patients agreed, she would lead them to an empty room, seat the patient on a chair facing away from her and record the cough. 

But what if she couldn’t get them to agree to the study. “Nothing. I would never insist. And I would keep checking on them either way,” she says. 

All of this was in the first few months of the data collection phase. Now, Mangal has graduated in her role. She visits multiple centres, spending two days in a week at a single centre. She now also supervises Wadhwani AI’s other data collection coordinators. “I have trained some of them and I advise data collectors on the best practices,” she says. To ascertain that processes are being followed, she makes surprise checks. 

Mangal has come a long way. Her college hasn’t started yet and she has decided she will volunteer with Wadhwani AI and DFY for as long as she can. She’ll probably visit her family another time. 

  • Wadhwani AI

    We are an independent and nonprofit institute developing multiple AI-based solutions in healthcare and agriculture, to bring about sustainable social impact at scale through the use of artificial intelligence.

ML Engineer


An ML Engineer at Wadhwani AI will be responsible for building robust machine learning solutions to problems of societal importance; usually under the guidance of senior ML scientists, and in collaboration with dedicated software engineers. To our partners, a Wadhwani AI solution is generally a decision making tool that requires some piece of data to engage. It will be your responsibility to ensure that the information provided using that piece of data is sound. This not only requires robust learned models, but pipelines over which those models can be built, tweaked, tested, and monitored. The following subsections provide details from the perspective of solution design:

Early stage of proof of concept (PoC)

  • Setup and structure code bases that support an interactive ML experimentation process, as well as quick initial deployments
  • Develop and maintain toolsets and processes for ensuring the reproducibility of results
  • Code reviews with other technical team members at various stages of the PoC
  • Develop, extend, adopt a reliable, colab-like environment for ML

Late PoC

This is early to mid-stage of AI product development

  • Develop ETL pipelines. These can also be shared and/or owned by data engineers
  • Setup and maintain feature stores, databases, and data catalogs. Ensuring data veracity and lineage of on-demand pulls
  • Develop and support model health metrics

Post PoC

Responsibilities during production deployment

  • Develop and support A/B testing. Setup continuous integration and development (CI/CD) processes and pipelines for models
  • Develop and support continuous model monitoring
  • Define and publish service-level agreements (SLAs) for model serving. Such agreements include model latency, throughput, and reliability
  • L1/L2/L3 support for model debugging
  • Develop and support model serving environments
  • Model compression and distillation

We realize this list is broad and extensive. While the ideal candidate has some exposure to each of these topics, we also envision great candidates being experts at some subset. If either of those cases happens to be you, please apply.


Master’s degree or above in a STEM field. Several years of experience getting their hands dirty applying their craft.


  • Expert level Python programmer
  • Hands-on experience with Python libraries
    • Popular neural network libraries
    • Popular data science libraries (Pandas, numpy)
  • Knowledge of systems-level programming. Under the hood knowledge of C or C++
  • Experience and knowledge of various tools that fit into the model building pipeline. There are several – you should be able to speak to the pluses and minuses of a variety of tools given some challenge within the ML development pipeline
  • Database concepts; SQL
  • Experience with cloud platforms is a plus

ML Scientist


As an ML Scientist at Wadhwani AI, you will be responsible for building robust machine learning solutions to problems of societal importance, usually under the guidance of senior ML scientists. You will participate in translating a problem in the social sector to a well-defined AI problem, in the development and execution of algorithms and solutions to the problem, in the successful and scaled deployment of the AI solution, and in defining appropriate metrics to evaluate the effectiveness of the deployed solution.

In order to apply machine learning for social good, you will need to understand user challenges and their context, curate and transform data, train and validate models, run simulations, and broadly derive insights from data. In doing so, you will work in cross-functional teams spanning ML modeling, engineering, product, and domain experts. You will also interface with social sector organizations as appropriate.  


Associate ML scientists will have a strong academic background in a quantitative field (see below) at the Bachelor’s or Master’s level, with project experience in applied machine learning. They will possess demonstrable skills in coding, data mining and analysis, and building and implementing ML or statistical models. Where needed, they will have to learn and adapt to the requirements imposed by real-life, scaled deployments. 

Candidates should have excellent communication skills and a willingness to adapt to the challenges of doing applied work for social good. 


  • B.Tech./B.E./B.S./M.Tech./M.E./M.S./M.Sc. or equivalent in Computer Science, Electrical Engineering, Statistics, Applied Mathematics, Physics, Economics, or a relevant quantitative field. Work experience beyond the terminal degree will determine the appropriate seniority level.
  • Solid software engineering skills across one or multiple languages including Python, C++, Java.
  • Interest in applying software engineering practices to ML projects.
  • Track record of project work in applied machine learning. Experience in applying AI models to concrete real-world problems is a plus.
  • Strong verbal and written communication skills in English.