Prompt Engineer

About AiSensy

AiSensy is a WhatsApp based Marketing & Engagement platform helping businesses like Adani, Delhi Transport Corporation, Yakult, Godrej, Aditya Birla Hindalco, Wipro, Asian Paints, India Today Group, Skullcandy, Vivo, Physicswallah, and Cosco grow their revenues via WhatsApp.

Enabling 210,000+ Businesses with WhatsApp Engagement & Marketing

800 Crores+ WhatsApp Messages exchanged between Businesses and Users via AiSensy per year

Working with top brands like Delhi Transport Corporation, Vivo, Physicswallah & more

High Impact as Businesses drive 25-80% Revenues using AiSensy Platform

Mission-Driven and Growth Stage Startup backed by Marsshot.vc, Bluelotus.vc & 50+ Angel Investors

About Role

AiSensy's Bot Builder powers AI agents for thousands of businesses across 15+ verticals — from automotive lead qualification to embassy crisis helplines to healthcare appointment booking. Our strategic accounts don't just want a tool; they want a partner who can take ownership of how their bot actually behaves with end customers on WhatsApp.

This role sits between our customers and our platform. You will own the prompt engineering, knowledge configuration, and ongoing tuning for our most important Bot Builder accounts — and you will own the relationship with those customers. You are the technical brain and the commercial face for these accounts.

If you've ever read a poorly performing chatbot's prompts and thought "I could fix this in an afternoon," and you can also walk into a room with a CMO and explain what their bot will and won't do, this role is for you.

What you will actually do

Build production-grade bots for strategic accounts (~60% of time)

• Design orchestration prompts, intent routing, and tool-call boundaries for customer bots

• Configure knowledge bases (RAG) and tune retrieval for accuracy and coverage

• Set up guardrails — advice boundaries, never-do rules — calibrated to each customer's compliance posture

• Build conversation flows that handle multilingual users

• Debug real production failures: tool calls being routed to RAG, fillers breaking conversational coherence, guardrails blocking valid queries, retrieval non-determinism, hallucinated answers

Own the customer relationship (~30% of time)

• Run discovery sessions to translate business goals ("reduce inbound lead handling cost by 40%") into bot specifications

• Drive onboarding for new strategic accounts end-to-end

• Run weekly/biweekly reviews on bot performance — deflection rate, resolution rate, hand-off accuracy, CSAT

• Lead QBRs with customer leadership; tell the story of impact with real data

• Spot expansion opportunities — new verticals, new flows, new channels — and close them

Build leverage across the team (~10% of time)

• Convert what works into reusable templates and playbooks the rest of the AM org can use

• Feed pattern observations back to the Bot Builder engineering team: where the platform is friction, what features would unlock the next class of customers

• Contribute to internal prompt libraries, eval suites, and quality benchmarks

What we are looking for

Required

• 2–5 years of experience in one or more of: customer success/AM for a technical product, applied AI/ML, technical consulting, solutions engineering

• Demonstrable hands-on prompt engineering experience — you can show us prompts you've written, tuned, and debugged

• Strong written communication — you can explain a complex bot behavior in three sentences a non-technical exec will understand

• Comfort with data — basic SQL, conversation analytics, A/B reasoning

• Genuine curiosity about how LLMs work — not just how to use them

You will stand out if you have

• Experience with WhatsApp Business API, chatbot platforms, or conversational AI products

• Worked on RAG systems, tool-calling agents, or multi-turn conversation design

• Built something on your own — a side project, an internal tool, a bot — that shipped to real users

• Multilingual capability, especially Hindi/Hinglish

You will not be a fit if

• You think prompt engineering means asking ChatGPT for marketing copy

• You want to manage a relationship without ever opening the system

• You want to engineer without ever talking to a customer