Hermeus is a venture-backed defense aviation company reclaiming the lost art of rapid iterative prototyping to build the fastest aircraft in the world today. By prioritizing relentless hardware iteration, we deliver high-speed systems at the pace of the modern battlefield. We work with the Department of War to provide the high-speed capabilities our nation and its allies need to maintain a durable, asymmetric advantage.
About The Role:
We are seeking a Senior AI Engineer, Internal AI Platforms to help design, build, and scale Cortex, our internal AI platform. Cortex is intended to become the centralized AI platform across the company - enabling employees to securely interact with internal knowledge, business systems, workflows, and future agentic capabilities within a highly governed environment.
This is a hands-on engineering role focused on building secure, scalable, production-grade AI systems for enterprise use. The ideal candidate has experience developing LLM-enabled applications, retrieval systems, and agentic workflows within regulated or security-conscious environments, and is comfortable operating across architecture, infrastructure, integrations, observability, and user experience.
Responsibilities:
Design, build, and improve Cortex, including retrieval systems, document analysis, workflow automation, and internal AI capabilities
Develop integrations with enterprise platforms such as Jira, Confluence, Microsoft 365, Slack/GovSlack, and internal business systems
Build and optimize RAG pipelines including ingestion, chunking, embeddings, vector search, permissions enforcement, and response evaluation
Develop agentic workflows that safely perform actions such as summarization, ticket updates, governed data access, and business process automation
Define architecture for secure self-hosted, private, or cloud-isolated AI systems within regulated environments
Partner with Security, IT, and Compliance teams to implement governance controls, auditability, permissions, and secure API access
Evaluate and integrate commercial, open-source, and cloud-native LLM providers and orchestration frameworks
Build observability into AI systems including monitoring, evaluation metrics, latency tracking, error handling, and workflow reliability
Contribute reusable AI engineering standards, patterns, and platform capabilities to support long-term internal AI adoption
Requirements:
5+ years of professional software engineering experience
2+ years building AI, ML, automation, or LLM-enabled applications in production environments
Strong programming experience in Python, TypeScript, or both
Hands-on experience building production AI systems using LLMs, RAG pipelines, vector databases, embeddings, and orchestration frameworks
Experience deploying scalable services in cloud or private infrastructure environments, preferably AWS
Experience building AI systems that integrate with enterprise platforms, APIs, and governed data sources
Strong understanding of security, permissions models, identity management, and enterprise data governance
Practical understanding of LLM limitations including hallucinations, prompt injection, data leakage, and evaluation challenges
Ability to operate in ambiguity, rapidly prototype solutions, and harden successful systems into production-ready platforms
Preferred Skills and Experience:
Aerospace, defense, national security, financial services, healthcare, or other regulated industry experience
Experience with AWS-native AI and infrastructure services including Bedrock, SageMaker, EKS, OpenSearch, or GovCloud
Familiarity with commercial and open-source model providers such as Anthropic Claude, OpenAI, Llama, Mistral, or similar
Experience with AI orchestration and agent frameworks such as LangChain, LlamaIndex, Semantic Kernel, CrewAI, or similar tooling
Experience with vector databases and search technologies such as OpenSearch, Pinecone, Weaviate, pgvector, or FAISS
Experience building AI evaluation pipelines including regression testing, retrieval scoring, and red-team validation
Familiarity with secure software development, DevSecOps, CI/CD, infrastructure as code, and observability tooling
Experience designing systems for CUI, ITAR, export-controlled, or otherwise sensitive data environments
Strong communication skills with the ability to explain AI architecture, risks, and tradeoffs to technical and non-technical stakeholders