AI Operations Associate — Voice Quality & Data - Fresher (WFH)
InstaBus Verified employer
Actively hiring · Posted 1mo ago · JEV26100F53ED9AB8
Job description
About the job:You are the human in the loop for an AI system that talks to thousands of passengers. Two things depend on you: the data our AI agent speaks from, and the judgement call on whether it spoke well. Both are the difference between an AI product that operators trust and one they switch off. This is not a ticket queue. You will sit between our operators, our AI and our product team, and you will be the first person to know when something is wrong.
Key Responsibilities:
A. AI Voice Quality Assurance
1. Listen to live AI call recordings daily and assess them against a quality rubric covering comprehension, response accuracy, tone, interruption handling, and call resolution.
2. Identify failure modes, including misheard place names, incorrect language switches, dropped context mid-call, awkward phrasing, and voice quality issues.
3. Log, categorise, and prioritise issues so the product team knows what to fix first.
4. Track whether fixes have worked from call to call.
5. Immediately flag anything that affects a passenger's real journey.
6. Provide notes that directly inform engineering changes to the agent, acting as the closest point of insight into the passenger experience.
B. Passenger Data Operations
1. Pull daily passenger manifests from operator GDS/back-office systems across multiple bus operators and routes.
2. Use AI tooling, including Claude, to clean, validate, and standardise manifests into the platform format, including deduplication, phone merging, name normalisation, boarding/drop point mapping, and agent-versus-OTA classification.
3. Cross-check every file against source totals and flag discrepancies before they reach the dashboard.
4. Push validated files to the InstaBus dashboard on schedule, including evening and night departure cycles.
5. Identify patterns in bad data and recommend ways to fix them at source, recognising recurring issues that may inform processing rules.
6. Operate an AI-assisted pipeline and remain accountable for its output, using prompting, correction, and quality assurance to manage the AI system.
How we work:
Hours and days are flexible. We don't run a fixed shift. What we need is roughly 8 hours of real work a day and coverage of the departure cycles; manifests are pulled and uploaded through the morning, evening, and late-night slots, and calls are reviewed daily. You'll plan your own week in coordination with the rest of the team and our interns, so that someone is always covering the cycles. If you want to take a Wednesday off and work Saturday, that's a conversation, not a problem.
This is a remote role. You'll need your own laptop, a reliable internet connection, and headphones good enough to judge call audio quality. We don't provide hardware.
Confidentiality is non-negotiable. You will handle real passenger names, phone numbers, and travel details. That data stays inside our systems, always. We'll ask you to sign an NDA.Who can apply:Only those candidates can apply who:are Computer Science Engineering studentsSalary:₹ 3,60,000 /yearExperience:No experience requiredDeadline:[hidden]:59:59Skills required:Attention to Detail, MS-Excel, Artificial intelligence, Generative AI Tools and ClaudeOther Requirements:Writing1. Fluency in Hindi and English, with comfort understanding naturally spoken Hinglish, as the role involves listening to calls rather than reading transcripts.2. Strong attention to detail, with the ability to identify discrepancies and investigate them.3. Comfort using Excel/Google Sheets and willingness to learn AI tools, with curiosity valued more than prior experience.4. Ability to write clearly, as issue logs serve as inputs for product improvement.5. Ability to work independently and manage daily tasks effectively, with performance measured by work quality and completion rather than hours worked.6. Any graduate; freshers are welcome.7. Bonus: Exposure to travel, transport, or logistics operations; customer support quality monitoring; or hands-on use of ChatGPT or Claude in professional work.About Company:InstaBus is building India's first AI Calling Agent SaaS for Intercity Bus Travel. Our AI voice platform automates passenger communication, end-to-end booking confirmations, boarding reminders, customer support, delay updates, feedback collection, and repeat sales, all in a human-like multilingual voice over phone and WhatsApp.
We operate at the intersection of AI, voice automation, and mobility, solving one of the biggest, most overlooked problems in India's 26,000 Cr private intercity bus industry.
Responsibilities
You are the human in the loop for an AI system that talks to thousands of passengers. Two things depend on you: the data our AI agent speaks from, and the judgement call on whether it spoke well. Both are the difference between an AI product that operators trust and one they switch off. This is not a ticket queue. You will sit between our operators, our AI and our product team, and you will be the first person to know when something is wrong.
Key Responsibilities:
A. AI Voice Quality Assurance
1. Listen to live AI call recordings daily and assess them against a quality rubric covering comprehension, response accuracy, tone, interruption handling, and call resolution.
2. Identify failure modes, including misheard place names, incorrect language switches, dropped context mid-call, awkward phrasing, and voice quality issues.
3. Log, categorise, and prioritise issues so the product team knows what to fix first.
4. Track whether fixes have worked from call to call.
5. Immediately flag anything that affects a passenger's real journey.
6. Provide notes that directly inform engineering changes to the agent, acting as the closest point of insight into the passenger experience.
B. Passenger Data Operations
1. Pull daily passenger manifests from operator GDS/back-office systems across multiple bus operators and routes.
2. Use AI tooling, including Claude, to clean, validate, and standardise manifests into the platform format, including deduplication, phone merging, name normalisation, boarding/drop point mapping, and agent-versus-OTA classification.
3. Cross-check every file against source totals and flag discrepancies before they reach the dashboard.
4. Push validated files to the InstaBus dashboard on schedule, including evening and night departure cycles.
5. Identify patterns in bad data and recommend ways to fix them at source, recognising recurring issues that may inform processing rules.
6. Operate an AI-assisted pipeline and remain accountable for its output, using prompting, correction, and quality assurance to manage the AI system.
How we work:
Hours and days are flexible. We don't run a fixed shift. What we need is roughly 8 hours of real work a day and coverage of the departure cycles; manifests are pulled and uploaded through the morning, evening, and late-night slots, and calls are reviewed daily. You'll plan your own week in coordination with the rest of the team and our interns, so that someone is always covering the cycles. If you want to take a Wednesday off and work Saturday, that's a conversation, not a problem.
This is a remote role. You'll need your own laptop, a reliable internet connection, and headphones good enough to judge call audio quality. We don't provide hardware.
Confidentiality is non-negotiable. You will handle real passenger names, phone numbers, and travel details. That data stays inside our systems, always. We'll ask you to sign an NDA.
Key skills
How to apply
- Sign in or create your free profile — takes about two minutes.
- Apply with one tap — your profile is shared directly with InstaBus.
- Track your application and get updates by email and WhatsApp.