About the role
As an AI Software Engineer, you'll bridge the gap between AI research and production systems. You'll implement robust AI integrations, optimize inference pipelines, and ensure our AI features are reliable, fast, and delightful to use.
Responsibilities
- Implement AI-powered features end-to-end, from API design to frontend integration.
- Build robust integrations with the major LLM providers.
- Optimize inference pipelines for latency and cost efficiency.
- Implement caching, batching, and other strategies for scalable AI systems.
- Build evaluation and monitoring systems for AI feature quality.
- Develop prompt engineering strategies and manage prompt versioning.
- Handle edge cases, errors, and fallbacks gracefully.
- Write comprehensive tests and documentation for AI systems.
Requirements
Experience
- 4+ years of software engineering experience.
- Experience integrating LLM APIs in production applications.
- Track record of shipping reliable, user-facing features.
Technical skills
- Strong proficiency in Python and/or TypeScript.
- Experience with REST API design and implementation.
- Familiarity with LLM concepts (prompting, context windows, token limits).
- Experience with async programming and concurrent systems.
- Knowledge of observability patterns (logging, metrics, tracing).
Nice to have
- Experience with vector databases and embeddings (Pinecone, Weaviate).
- Background in RAG (Retrieval Augmented Generation) systems.
- Experience with streaming responses and real-time AI features.