ML Engineer, Agentic Systems

Sourced from careers.bu.edu

Build production agentic applications that automate complex geoscience workflows, including agent-based systems, tool and API integration, persistent state management, and context retrieval. Design and execute LLM fine-tuning strategies when model adaptation is required. Deliver well-tested services with lightweight web interfaces for operators and end users, and help shape which workflows to automate and where humans stay in the loop.

• Design agent workflows with branches, loops, sub-workflows, and explicit routing
• Implement human-in-the-loop approvals and agent action permissions
• Provide agents with context via tool-based search, SQL, and semantic retrieval with reranking
• Integrate tools and external APIs, handling concurrency, retries, and error paths
• Add database-backed persistence so workflows can pause and resume reliably
• Design and execute LLM fine-tuning strategies (LoRA, DPO, GRPO) with evaluation sets and rollback criteria
• Instrument agent runs with tracing and continuous evaluation
• Deliver production-ready services with automated tests, CI/CD, and APIs
• Leverage AI coding agents such as Claude Code or Codex responsibly

• Bachelor's degree or higher in Computer Science, Engineering, Physics, Mathematics, Geophysics, or related field
• Minimum cumulative GPA of 3.5 on a 4.0 scale
• Strong programming and software engineering fundamentals, including asynchronous and concurrent programming
• Hands-on experience building multi-agent or graph-based LLM workflows
• Experience designing agent information retrieval with tool-based search and semantic retrieval
• Practical LLM fine-tuning experience with parameter-efficient methods such as LoRA
• Experience with tracing and evaluation of LLM applications
• Experience building web services and APIs (e.g., FastAPI) with PostgreSQL, Docker, and Git

• Experience designing complex agent systems with task decomposition and parallel execution
• Hands-on experience with LLM post-training techniques such as DPO and GRPO
• Experience running enterprise-scale applications in production
• Prior work in workflow automation or geoscience/scientific computing
• Frontend experience building operator dashboards