Related skills
python llm openai vector databases retrievalπ Description
- Design and deliver production AI systems across document intelligence.
- Own architecture for LLM-based systems, including retrieval.
- Build evals, observability, and performance monitoring.
- Cost and latency optimization in production AI.
- Partner with AI Product and Engineering to scope AI features.
- Ship quickly and scale impact with AI.
π― Requirements
- 6+ years software engineering; 2+ yrs shipping LLM/ML systems
- Designing and deploying agentic systems (tool use & orchestration)
- Strong Python production-grade coding, testing, deployment
- LLM APIs (OpenAI, Anthropic, Bedrock); prompting and function calling
- Evals and observability for LLM systems
- Retrieval systems (RAG) with vector DBs and embeddings
π Benefits
- Work from home, in-office, or on the move
- PTO as needed, comprehensive insurance
- 401(k) match, stock options, and stock purchase plan
Meet JobCopilot: Your Personal AI Job Hunter
Automatically Apply to Engineering Jobs. Just set your
preferences and Job Copilot will do the rest β finding, filtering, and applying while you focus on what matters.
Help us maintain the quality of jobs posted on Empllo!
Is this position not a remote job?
Let us know!