Generative AI Engineer

Summary of Responsibilities:

We are building a next-generation conversational AI platform (voice and text). We are looking for an engineer with strong hands-on experience in Python and modern AI systems.

Responsibilities by Function:

● Build, optimize, and maintain LLM-powered features, including RAG pipelines and agentic workflows.

● Develop backend services using FastAPI and integrate multiple LLM providers.

● Work with Pipecat for voice pipelines and real-time conversational systems.

● Analyze data, identify gaps, and implement improvements to model quality and system performance.

● Collaborate with product and engineering teams to ship reliable, production-ready AI features.

Qualifications:

● 4–6 years of experience in Python software engineering.

● Strong practical experience with LLMs, RAG, embeddings, vector stores, and agentic AI.

● Experience building APIs/services using FastAPI.

● Experience with voice/real-time systems or Pipecat is a plus.

● Ability to evaluate data pipelines, debug issues, and make data-driven improvements.

● Solid understanding of software engineering best practices and production deployment.