Related skills
python langchain llamaindex vector dbs async programmingπ Description
- Design and build GenAI systems turning LLMs into dependable tools with retrieval and tool use.
- Collaborate with ML/infra engineers to scale GenAI workflows, manage latency.
- Write modular, robust code thatβs fault-tolerant and easy to iterate on.
- Own architectural decisions for workflows, data flow, state, and outputs.
- Drive evaluation: benchmarks, automated and human-in-the-loop tests, AB experiments.
- Leverage frontier capabilities: prototype with new models/tools and prompting techniques.
π― Requirements
- 3+ years building production-grade systems; 1β2+ years on GenAI/LLM products.
- Deep fluency with LLM APIs, prompting, and orchestration (LangChain, LlamaIndex).
- Retrieval systems, vector DBs, kNN; function calling and tool-use.
- Model evaluation with diverse datasets, automated and human-in-the-loop evals; A/B tests.
- Strong Python fundamentals; async programming, performance profiling, packaging.
- Must be willing to work from SF office at least 3x per week.
π Benefits
- Relocation assistance for SF relocation.
- Generous time off and flexible PTO.
- Medical, Dental, and Vision coverage for full-time employees.
- 401(k) matching.
- Personal device allowance.
- Mental health support and parental leave.
π Relocation support
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!