Staff Machine Learning Engineer, SecureAI

About the Role

What You'll Do

• Implement intent-based enforcement for agent runtime requests.
• Use LLM reasoning and prompt parsing to interpret prompts, tool payloads, and intent in real time.
• Integrate low-latency inference or semantic evaluation engines into API gateway request paths.
• Use embeddings, vector search, or zero-shot classification to score intent and action alignment.
• Feed semantic verification results into confidence-scored policy decision engines such as Cedar.
• Establish evaluation benchmarks, prompt-injection defenses, and guardrails.
• Architect scalable ML and GenAI systems spanning retrieval, inference, and evaluation.
• Optimize prompting, context retrieval, and RAG workflows for Claude-based systems.
• Build automated evaluation pipelines for model quality, correctness, groundedness, and safety.
• Implement schema validation, structured outputs, and guardrails for reliable AI outputs.