Location: Mountain View CA Hybrid (3 days a week onsite)
What youll do
- Design build and ship GenAI solutions from prototype to production.
- Architect RAG pipelines leveraging large language models.
- Lead prompt engineering: system/tool prompts function calling prompt versioning with offline/online evals.
- Implement evaluation & observability with ground source of truth establishment confusion metrics LLM-as-judge with human review cost & latency monitoring.
- Proficiency in Python and experience with LangChain/LlamaIndex (or equivalent).
- Deep understanding of retrieval strategies prompt patterns model context management and hallucination mitigation.
- Experience with cloud LLM providers (Azure OpenAI AWS Bedrock Vertex AI) and orchestration (Airflow/Dagster).
- Security/privacy mindset (PII handling RBAC) and practical cost/performance tuning.
- Partner with product design legal/security to ensure safety privacy and measurable business impact.
Success looks like
- A production prompt running pipeline system with clear quality lift (accuracy/confusion metrics) and reduced hallucinations-backed by a repeatable eval harness.
What we are looking for
- 5 Years of relevant experience as an AI Engineer
- Good communication skills
- Team Player
- Available to start immediately