Backend Engineer – ChaturAI in New Delhi | RightWalk Foundation

RightWalk Foundation

RightWalk Foundation works with state governments across India to make sure the rights and benefits already written into law actually reach the families they were meant for. Many people never receive what they are entitled to simply because the process to claim it is confusing or hard to reach. RightWalk closes that gap by working inside government systems, not around them, so that change lasts. One of its tools is ChaturAI, a WhatsApp-based assistant that walks citizens through NAPS apprenticeship registration and RTE Gujarat school admissions, and completes the government portal steps for them in the background. This role sits within RightWalk Foundation's technology team, which builds and runs the systems behind ChaturAI.

Role

You will own the server side of ChaturAI: the Go backend that runs the agent loop and holds conversation state, the Python MCP servers that automate the NAPS and RTE portal journeys, and the PostgreSQL and pgvector data layer beneath them. You will report to the Engineering Lead for ChaturAI and work closely with AI and prompt engineers and with the programme team in Delhi. This is a high ownership role: government portals change without warning, and thousands of families may arrive on WhatsApp in a single week during a state campaign, so the services you build need to stay correct, observable and easy to recover.

Responsibilities

• Own the Go backend that receives Chatwoot webhooks, manages the request lifecycle and stores conversation state in PostgreSQL.
• Drive the agent orchestration loop, including tool call routing, iteration limits, timeouts and error handling, so no user message ever ends in silence.
• Design and version the HTTP endpoints and webhook contracts the rest of the stack depends on.
• Own the Python MCP servers that automate the NAPS and RTE Gujarat portal journeys from start to finish.
• Build and extend the MCP tool catalogue with new tools, schema changes and backward compatibility for the agent.
• Lead diagnosis and repair when a government portal changes its markup, flow or login, with same day turnaround as the standard.
• Harden automation against unreliable upstream portals using retries, idempotency and failure states that are clear to the user.
• Own the data model across the portal and bot databases, including migrations and the pgvector collections behind retrieval.
• Integrate and run external services: Meta WhatsApp Cloud API, Chatwoot and the OpenAI or Bedrock completion APIs.
• Protect personal data by storing as little as possible and keeping beneficiary details out of logs and prompts.
• Own service reliability, alerting and incident response for the ChaturAI backend, including OpenTelemetry tracing into SigNoz, Docker builds and CI pipelines.
• Translate needs from the NAPS and RTE programme teams into technical scope and honest timelines, and keep documentation good enough for a new engineer to run the stack locally on day one.

Requirements

• B.E. or B.Tech or equivalent in Computer Science or a related field.
• Strong self taught engineers with a proven production track record will also be considered.
• 3-5 years building and running production backend services.
• Production ownership of at least one live service.
• Strong in Go, including HTTP services, concurrency and clean webhook and API design.
• Strong in Python, including async service work with FastMCP and resilient automation of third party web portals.
• Willingness to work in both Go and Python daily, as this stack is not single language.
• PostgreSQL skills covering schema design, migrations and query tuning, plus pgvector for retrieval.
• Comfort working in a small team with no dedicated DevOps or QA layer, taking your own service to production and keeping it running.
• A calm and systematic approach to debugging when a government portal breaks in the middle of a campaign.
• Ownership: you take a problem all the way to done in production without being chased.
• Motivation that comes from families receiving their entitlements, not only from clean architecture.
• Professional English; working Hindi is useful for collaborating with the programme team.
• Helpful to have: exposure to LLM or agent systems, MCP and tool calling architectures, WhatsApp or messaging platforms, or Indian government portal integrations.

Benefits

• Direct ownership of a production AI system that citizens use to claim government entitlements.
• Compensation benchmarked to the Indian social sector technology market and set according to experience.
• Work alongside AI and prompt engineers and a programme team that sits close to state governments.
• Wide technical scope across Go, Python, PostgreSQL, pgvector, WhatsApp Cloud API and OpenTelemetry.
• A small, high trust team where your work reaches families claiming apprenticeships and school admissions.

Apply

Interested candiadtes can apply through the link given below

Apply

Follow our WhatsApp Channel to get notified about the latest jobs.