Remote Forge AI Engineer — Build Agentic Platform

Norstella; Richmond (VA); Remote; USD 140,000 - 190,000; Full time

Job summary

Norstella is seeking a Senior Forge AI Engineer to join our remote US team. You will build a greenfield, agentic platform and own design across the Forge chain from orchestration to memory management.

You’ll work with Python and TypeScript, design multi-agent coordination, MCP servers, RAG pipelines, and safety primitives to ensure trustworthy production systems.

The role requires 6+ years in software engineering and a proven track record delivering production AI or agentic projects.

Qualifications

• 6+ years of software engineering experience in production AI/agentic systems.
• Experience with an agentic framework and MCP servers.
• Strong Python or TypeScript fundamentals.
• Experience with memory architectures and RAG patterns.
• Knowledge of AI safety practices (OWASP LLM Top 10).

Responsibilities

• Design agents across the Forge chain — orchestration, tool-use surfaces, MCP server integrations, prompt and RAG pipelines.
• Own multi-agent coordination architecture: inter-agent trust boundaries, message contracts, partial failure handling and recovery.
• Build and evolve the MCP server layer — tool schema design, capability contracts, versioning.
• Design agent memory and state management: context window strategy, long-term memory, persistence across steps.
• Own agent quality end-to-end: eval harnesses, benchmarks, continuous evaluation pipelines, gate criteria for releases.
• Instrument agent observability — token tracing, tool-call chain logging, cost attribution per run.

Skills

Python

TypeScript

Agentic systems

RAG pipelines

Memory architectures

Prompt engineering

AI safety

Tools

MCP server

LangGraph

CrewAI

Autogen

Semantic Kernel

Job description

Norstella is seeking a Senior Forge AI Engineer to join our remote US team. You will build a greenfield, agentic platform and own design across the Forge chain from orchestration to memory management.

You’ll work with Python and TypeScript, design multi-agent coordination, MCP servers, RAG pipelines, and safety primitives to ensure trustworthy production systems.

The role requires 6+ years in software engineering and a proven track record delivering production AI or agentic projects.