Write, test, and iterate prompts for LLM-powered voicebots and chatbots.
Design conversation flows for real-world enterprise use cases.
Develop tool-calling logic and guardrails for LLM applications.
Design multi-turn and multi-intent conversational experiences.
Support multilingual conversational AI scenarios.
Configure and tune speech pipelines involving STT, LLM, and TTS.
Evaluate speech recognition and speech synthesis performance.
Analyze accuracy, latency, and naturalness of voicebot interactions.
Perform root cause analysis using conversation and application logs.
Trace errors and investigate unexpected bot behavior.
Propose fixes for conversational AI issues.
Build and run QA and evaluation frameworks for AI systems.
Measure conversation quality against predefined parameters.
Prepare test cases before customer launches.
Validate conversational flows before production deployment.
Support client rollouts and resolve issues after launch.
Document configurations, findings, and AI delivery best practices.
Collaborate with technical and non-technical stakeholders.
Skills & Eligibility
Experience: 0–1 years; suitable for entry-level candidates and interns.
Technical Background: Engineering or equivalent hands-on technical grounding.
Programming: Working knowledge of Python.
APIs: Understanding of REST APIs and system integrations.
Data Formats: Comfortable working with JSON.
Generative AI: Exposure to Large Language Models such as GPT, Claude, Gemini, or similar systems.
Prompt Engineering: Practical experimentation with prompts and an understanding of basic LLM behavior.
Speech Technology: Basic understanding of Speech-to-Text / Automatic Speech Recognition and Text-to-Speech.
Conversational AI: Familiarity with chatbots, voicebots, or conversational AI through projects or personal experimentation.
Debugging: Strong problem-solving and root cause analysis skills.
Communication: Clear written and verbal communication.
Learning Ability: Ability to quickly learn new tools, technology stacks, and monitoring systems.
💡 Pro Tip: Want to build stronger practical skills in AI engineering, LLMs and generative AI? Check out The AI Engineer Course 2025 before your interview.
The job description identifies several skills that can provide an advantage even though they are not presented as the core requirements.
Candidates who have built applications using LLM APIs can demonstrate practical understanding of how AI models are integrated into applications.
Experience with prompt frameworks, agentic AI, or tool-calling systems can also be useful because modern conversational AI applications often need LLMs to interact with external tools and APIs.
Exposure to telephony and voice platforms is another advantage. Candidates interested in Indian-language NLP or multilingual AI can also differentiate themselves because the role involves multilingual conversational experiences.
Experience in QA, AI evaluation, automated testing, or conversation quality assessment can further strengthen an application.
The AI Delivery Intern position is based in Bangalore.
The supplied job description explicitly states that the team works five days a week from the office. Candidates should therefore be prepared for a full-time work-from-office arrangement rather than a remote or hybrid internship.
Note: This job is posted on external sites. Joblit shares the listing for convenience and does not take responsibility for third-party content.