AI Voice Agent Engineer (Fresher/Entry-Level)

Location:

Company:

Role Overview

We're looking for a passionate fresher or recent graduate excited about AI, audio tech, and real-time interaction. You will build and improve AI voice agents, audio streaming systems, educational interactions, and the infrastructure that supports them. You don't need to know everything on day one, as long as you are curious, learn fast, and love building things.

What You'll DoCore Technical Responsibilities

• Build and maintain

  real-time AI voice agents

  that interact naturally with kids.
• Work with

  streaming audio pipelines

  (WebRTC/WebSockets, Opus/PCM, Whisper, real-time TTS).
• Integrate ASR, TTS, LLMs, and agent frameworks into cohesive experiences.
• Implement

  tool-calling

  and function-calling workflows that allow agents to act intelligently.
• Build vector database pipelines (Pinecone, Chroma, Weaviate, Qdrant) for memory and personalization.
• Write clean, modular, async-friendly

  Python

  code (FastAPI, pydantic, asyncio).
• Collaborate with design and content teams to bring interactive, educational moments to life.
• Debug latency, concurrency, and real-time performance issues.
• Test and fine-tune agent behaviors for clarity, speed, and child-friendliness.
• Love experimenting with new frameworks, APIs, and ideas.
• Can work in a fast-moving startup with creativity and ownership.

Required Skills & Qualifications

• Bachelor's degree in CS, Engineering, AI/ML, or related fields.
• Strong Python skills (projects, internships, coursework, or personal builds count).
• Experience building

  voice agents

  , chatbots, audio apps, or interactive AI projectseven hobby projects.
• Understanding of

  ASR

  (Whisper, Azure Speech, Google STT, Deepgram)
• Knows

  TTS

  (Azure, OpenAI Realtime TTS, Coqui, etc.)
• Understands

  LLMs

  (OpenAI, Anthropic, function calling, agent frameworks)
• Understands

  Vector databases

  (FAISS, Pinecone, Chroma, Qdrant)
• Familiarity with WebSockets, REST APIs, basic concurrency (asyncio), or event-driven systems.
• Good debugging, problem-solving, and documentation skills.
• Strong communication and collaboration skillsespecially with non-technical teams.

Nice-to-Have Skills

Not requiredgreat if you've touched any of these.

• WebRTC or audio streaming pipelines
• Experience building apps for kids
• Understanding of child psychology or educational content
• Projects involving characters, storytelling, or game mechanics
• Basic ML inference or optimization
• Experience with cloud providers (AWS, GCP, Azure)

Note to Freshers

all count

If you've built anything involving audio, agents, LLMs, or kid-focused apps, we want to see it.

CTC : 4-7LPA depending on candidates expertise.

Interested candidates please fill this google form :https://forms.gle/WnP8UF64tNDBFmJq8

Note: Only Selected candidates will be reached out in next 4-6 days.