Lemonvolt is building production-grade, voice-first AI applications used by real businesses.

We are looking for a Senior AI Engineer who has shipped AI-powered systems to production, supported them post-launch, and understands reliability, scale, and security in real-world environments.

This role is hands-on and backend-heavy.

You will own AI workflows end-to-end from model integration to deployment, monitoring, and incident response.

Core Responsibilities :

- Design, build, and maintain production AI services using Python and Django/FastAPI

- Build and operate voice and chat agents integrating ASR/TTS and LLMs

- Implement robust agent workflows with tool/function calling and multi-step logic

- Integrate AI systems with databases and third-party SaaS APIs

- Own production deployments, releases, rollbacks, and ongoing support

- Implement background processing, retries, idempotency, and fault tolerance

- Add logging, metrics, tracing, and alerting for AI systems

- Write Runbooks and production documentation

- Troubleshoot live production issues and performance bottlenecks

Required Skills & Experience :

- 5+ years professional experience in backend or AI engineering

- Strong Python experience with Django and/or FastAPI in production

- Proven experience shipping AI or LLM-powered features to production

- Experience integrating LLM APIs (OpenAI, Azure OpenAI, Anthropic, etc.)

- Experience with voice or real-time systems (ASR/TTS or WebSocket-based systems)

- Solid understanding of background processing (Celery/RQ) and async workflows

- Strong PostgreSQL and Redis experience

- Docker-based deployment experience; comfortable with Linux environments

- Experience operating production systems (monitoring, on-call, incident response)

- Strong API integration skills with third-party platforms

- Clear written communication and documentation habits

Nice to Have (Not Required) :

- Experience with vector databases (pgvector, Qdrant, FAISS)

- Experience with RAG systems and document ingestion pipelines

- Experience deploying or operating self-hosted LLMs

- Familiarity with observability tools (Sentry, Open Telemetry, Prometheus)

- Exposure to WebRTC or real-time audio pipelines

Tech Stack :

- Python 3.11+, Django, Fast API, PostgreSQL, Redis, Celery, Web Sockets, LLM APIs, Vector Databases, Docker, CI/CD, Cloud Hosting (Render or similar)

What Success Looks Like :

- AI features released to production with minimal incidents

- Stable, observable AI services with clear runbooks

- Fast iteration without sacrificing reliability or security