Beacon AI
Software Engineer, Artificial Intelligence/LLM
- Confirmed live in the last 24 hours
- $135k–$168k
- Mid level
- Full-time
- Hybrid · San Carlos, California, United States
- 2+ yrs exp
- Added 3 weeks ago
About this role
Beacon AI is seeking a Software Engineer to build and maintain LLM-powered features within a safety-critical aviation environment. This role focuses on end-to-end development, from designing retrieval flows to monitoring performance in production, collaborating with product and infrastructure teams to deliver reliable and efficient AI solutions. You'll be working with established patterns and frameworks, guided by senior engineers.
What you'll do
- Design and implement retrieval-augmented generation and tool-calling flows.
- Build and maintain APIs and worker services in Python or TypeScript.
- Develop offline and online evaluations for prompt, retriever, and tool performance.
- Implement safety checks, PII redaction, and access controls.
- Optimize caching, request shaping, and prompt templates to control latency and cost.
- Maintain and refresh knowledge bases with data from various sources.
What they're looking for
- RAG (Retrieval-Augmented Generation)
- Tool-calling
- Python
- TypeScript
- LangChain
- Vector Search
- AWS Bedrock
Opens the application — the Jobs AI extension fills it for you. Set up autofill
Opens the official application on the employer’s site. No login required.
Beacon AI
Likely interview questions
- Describe a time you implemented a RAG system. What challenges did you face, and how did you overcome them?
- How do you approach designing and implementing error handling and fallbacks in a production LLM application?