Empowering the Asha worker

There were over 850,000 Ashas across India. AI help make their job easier and reduce errors.
One of the first missions of the Asha program was to encourage families to visit hospitals and healthcare centres when they were about to deliver a child.

Asha in Hindi means hope. In 2005, the government of India, as part of the National Rural Health Mission, started the Asha (Accredited social health activist) worker program. It was meant to be a beacon of light aimed at protecting the health of women in India’s rural populace. In rural India, people tend to avoid doctor visits as much possible. In fact, 61% of India’s births are at home. This brings with it a score of possible health issues for both mother and the child. One of the first missions of the Asha program was to encourage families to visit hospitals and healthcare centres when they were about to deliver a child. 

But let’s hit the brakes for a second. Asha program? Asha health workers are women from a district, employed by the Central government, who have at least primary education, are assigned to visit households across the length and breadth of the country. They are, so to speak, the eyes and ears of decision-makers in New Delhi. Their reports and observations are designed to be the bedrock of policy. As time passed, the Asha workers would administer first aid, refer patients to doctors and discuss contraception. 

According to data released by the government in 2013, there were over 850,000 Ashas across India. So effective was this program that the government tasked them to do preliminary screenings during the pandemic where they met families, asked them symptoms, advocated mask use and documented progress. 

Let’s zoom in

A June 2019 Unicef report estimates that over 20 million babies – over 14% of all the live births across the world annually – fall below the threshold birth weight of 2.5 kg. 

A University of Rochester Medical Centre , recommends that low-birth-weight babies be placed in a neonatal intensive care unit in a temperature-controlled bed. Rural India cannot replicate these services. Care for these babies is important. Low-birth-weight babies are not just at risk of dying, their weight can cause several developmental and health issues later in its life. Babies born under 2.5kg are at risk of lifelong health problems, including diabetes, obesity, development delays and low IQ. 

Research suggests that all of this is preventable if the baby’s weight can be determined in the first week after birth – an enormous problem in countries such as India where over 61% of births still take place at home, with no trained midwife or medical professional in attendance.

That’s where Asha workers step in. There are simple solutions such as holding the baby close to the mother, avoiding bathing the baby, feeding her frequently. And the first step is identification. Asha workers often suggest that the mother visit primary healthcare centres. But that’s a hurdle in itself, women tend not to go to a centre because it may mean loss of wages within the family, some can’t afford to travel long distances if the centres are further away. 

So, the only other solution was to weigh the babies at home. The results are, let’s just say, interesting. 

The chances of human error are high.

Leaving aside the huge coincidence, there is a problem in weighing babies. Another problem is some communities don’t allow outsiders to touch babies in the first few weeks of birth. In many cases, the scales are broken or improperly calibrated, so readings are off the mark. Even if the scale is accurate, the extension worker submits these readings to a data entry operator who may make input errors. Even when healthcare workers use digital scales, errors could still creep in due to the baby moving during the weighing process or the scale not being calibrated accurately. The chances of human error are high.

The role AI can play

The answer we have chosen is to use AI. Wadhwani Institute for Artificial Intelligence calls it the visual weighing machine. This is how it works, the Asha worker takes a short video of the baby using a basic smartphone, Wadhwani AI’s model converts this 2D video into a 3D image. And can potentially calculate not just the weight of the baby but also the circumference of the head and other critical characteristics which would help in identifying the health of the baby. Because it is on the phone, it can update a central database, hence eliminating human errors almost completely. 

It’s that simple. This doesn’t replace the Asha worker but empowers her. Empowers her to help multiple mothers and their children and take one step towards eliminating the problem of low birth weight babies.

ML Engineer

ROLES AND RESPONSIBILITIES

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.

DESIRED QUALIFICATIONS

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

Programming

  • 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
mle

ML Scientist

ROLES AND RESPONSIBILITIES

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.  

REQUIREMENTS

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. 

DESIRED QUALIFICATIONS

  • 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.
mls