Machine Learning Engineer

Prompt Engineering – Design, test, and refine prompt strategies to drive optimal agent behavior across diverse use cases.

Context Orchestration – Build pipelines integrating RAG, knowledge graphs, APIs, and layered memory (short-term, long-term, episodic).

Optimization – Optimize token usage and context allocation for long-running, multi-turn, and multi-agent workflows.

Reusable Blueprints – Develop reusable interaction templates and context blueprints for engineering and product teams.

Compliance & Guardrails – Implement safety, compliance, tone, and brand guardrails in agent workflows.

Continuous Improvement – Use execution traces, feedback, and automated evaluation to improve agent responses.

Experimentation – Conduct A/B testing on prompt and context variations to measure accuracy, latency, and cost trade-offs.

Knowledge Management – Maintain a central library of tested interaction patterns and context management strategies.

• Research Tracking – Stay updated on multi-agent orchestration frameworks and the state of AI interaction design.