Backend Software Engineer - AI/LLM & Voice Systems

About the Role:

We're seeking a Backend Software Engineer with expertise in Large Language Model (LLM) integration and voice interface systems. In this role, you'll build and maintain scalable systems that power intelligent agents, voice assistants, and real-time AI applications. This is a cross-functional role that blends traditional backend engineering with modern AI tooling and audio systems - ideal for a multidisciplinary technologist.

Responsibilities:

Design, develop, and optimize backend APIs using Python (FastAPI or Flask)

Build and deploy LLM pipelines using OpenAI, Anthropic, Mistral, Meta (LLaMA)

Implement ASR and TTS systems with Whisper, DeepSpeech, Google STT, Amazon Polly, Coqui TTS

Architect real-time pipelines using WebSockets, Redis Pub/Sub, microservices

Integrate RAG pipelines using FAISS, Pinecone, and LangChain/Haystack

Secure backend endpoints with JWT/OAuth2 and rate-limiting

Deploy on AWS/GCP using Lambda, Cloud Run, ECS, Docker, Kubernetes

Collaborate with frontend/mobile teams for multimodal interaction

Contribute to prompt tooling, memory systems, and agent orchestration

Design with cost-awareness in mind, optimizing cloud usage and minimizing overhead for model inference and streaming pipelines

Core Skills & Traits:

Strong software architecture design for real-time, low-latency systems

Deep understanding of LLM behavior in production and inference workflows

Experience building multimodal (voice + text) interfaces

Passion for building robust AI systems and developer tooling

Excellent collaboration and communication across disciplines

Security-first mindset in all aspects of data and system design

Cost-aware mindset: ability to evaluate tradeoffs and reduce infrastructure/inference costs