AI Engineer Intern

About the job

Type: Internship - Engineering – AI/ML About the Role We are looking for a hands-on AI Engineer Intern who can help us build production-grade voice agents using modern generative-AI stacks such as VAPI, ElevenLabs, Play.ai, Deepgram, OpenAI Realtime, or similar platforms. This role is ideal for someone who is naturally curious, learns independently, and loves staying ahead of the rapidly-changing AI landscape. What You’ll Do • Build, test, and deploy real-time voice agents that handle live customer conversations end-to-end. • Use tools like VAPI, ElevenLabs, Deepgram, Whisper, Speechmatics, or other voice stacks. • Prototype quickly, iterate aggressively, and turn early MVPs into production-ready agents. • Integrate LLMs with telephony tools, APIs, vector DBs, and backend workflows. • Analyze and improve conversational flows, latency, hallucinations, and overall reliability. • Work closely with senior engineers and founders on real customer deployments. • Continuously self-learn emerging tools, frameworks, and model capabilities—and bring new ideas to the team. What Makes You a Great Fit • Proven work: You’ve built at least 1–2 working voice agents or AI projects (personal, academic, hackathon, internship). • Strong understanding of LLMs, prompts, retrieval, and foundational agent concepts. • Experience with TTS/ASR providers (ElevenLabs, Deepgram, Whisper, etc.). • Solid programming skills (Python or JS/TS preferred). • Ability to thrive in a fast-paced, iterative, startup-style environment. • Self-learner with a habit of exploring new tools, reading docs, watching updates, and experimenting independently. • Passionate about generative AI and excited by weekly releases of new models, techniques, and frameworks. Bonus Skills (Nice to Have) • Experience with VAPI, PlayAI, Retell, or other voice agent frameworks. • Familiarity with RAG, embeddings, and vector databases (Pinecone, Weaviate, Chroma). • Understanding of real-time system optimizations and low-latency design. • Experience deploying apps or agents to cloud platforms (AWS, GCP, Vercel). Why Join Us • Build real production voice agents used by actual customers—not classroom demos. • Work directly with founders and senior engineers solving cutting-edge problems. • Learn extremely fast: 3 months here = 12 months anywhere else. • High ownership, real impact, and potential to convert to a full-time role.

Requirements

• Python
• LLMs
• Voice Agents

Preferred Technologies

• Python
• LLMs
• Voice Agents

Benefits

• Work from home