Senior Forge AI Engineer: Build Autonomous Agentic Platform

Norstella; Topeka (KS); Remote; USD 150,000 - 190,000; Full time

Job summary

Norstella is seeking an experienced Senior Forge AI Engineer to help build Forge, a greenfield agentic platform, in a remote US setting. You will work across orchestration, memory, MCP server design, and RAG pipelines to create trustworthy, scalable AI agents for life sciences applications.

You will own multi-agent coordination, tool-use APIs, and safety primitives, while advancing agent memory and evaluation methodologies.

Qualifications

• 6+ years of software engineering experience, including 2+ years with LLM-powered or agentic systems in production.
• Production experience with at least one agentic framework and a clear MCP server focus.
• Hands-on authoring of MCP servers or tool-use APIs with capability contracts and versioning.
• Experience with agent memory architectures and multi-step workflows.
• Strong Python and/or TypeScript skills; ownership of production agent code.
• Fluent in prompt engineering, tool/function calling, and multi-step orchestration.
• Knowledge of RAG patterns, vector databases, and LLM evaluation methodologies.

Responsibilities

• Design and build agents across the Forge chain with orchestration and RAG pipelines.
• Own multi-agent coordination architecture, trust boundaries, and recovery.
• Evolve the MCP server layer with design contracts and versioning.
• Design memory and state management for long-running multi-step workflows.
• Ensure end-to-end agent quality with eval harnesses and benchmarks.
• Instrument observability: tracing, logging, and cost attribution per run.
• Implement safe-by-design primitives: least-privilege tool-use and data handling.

Skills

Python

TypeScript

Prompt engineering

Agentic systems

LLM evaluation

RAG patterns

Vector databases

AI safety

Tools

LangGraph

CrewAI

Autogen

Semantic Kernel

MCP

tool-use APIs

Job description

Norstella is seeking an experienced Senior Forge AI Engineer to help build Forge, a greenfield agentic platform, in a remote US setting. You will work across orchestration, memory, MCP server design, and RAG pipelines to create trustworthy, scalable AI agents for life sciences applications.

You will own multi-agent coordination, tool-use APIs, and safety primitives, while advancing agent memory and evaluation methodologies.