Software Engineer, Internal AI Systems
Role details
Job location
Tech stack
Job description
We are looking for a mid-level Software Engineer to maintain, improve, and expand our internal AI software stack. This role will inherit an existing in-house AI environment and continue building on it to improve developer productivity, knowledge access, workflow automation, and internal business operations.
This is an applied engineering role, not machine learning research. The ideal candidate is a strong software engineer who is deeply curious about modern AI tools-LLMs, RAG systems, agents, code assistants, and automation platforms. They experiment with AI tools independently, understand the current landscape, and can clearly explain what AI is useful for, what it isn't, and how to apply it safely in an environment handling sensitive data. They thrive with ambiguity, actively explore new technology, and balance enthusiasm with healthy skepticism about AI's capabilities.
The role works closely with the Chief Engineer and engineering leadership to maintain the current AI stack, identify opportunities for improvement, build new AI-powered workflows, and help other engineers adopt AI tools effectively.
The ideal candidate is a curious and practical builder who can independently identify opportunities where AI or automation could improve workflows. They communicate ideas clearly, teach other engineers how to use new tools, and explain technical tradeoffs to leadership. Success means maintaining and improving our internal AI systems, building useful tools that others actually use, and keeping the company current with practical AI developments without chasing hype., * Maintain and improve the company's internal AI software stack, including chatbots, RAG-based knowledge bases, AI agents, code assistance tools, and workflow automation.
- Build internal tools and automation that improve engineering, management, documentation, code review, knowledge retrieval, and other business workflows.
- Design and extend backend services, APIs, integrations, and internal applications using Python, JavaScript/TypeScript, and related technologies.
- Work with on-premises and controlled AI infrastructure (including Anthropic and OpenAI models) where sensitive or government-related data must remain within company-controlled systems.
- Maintain Docker-based deployments and internal Linux server environments.
- Support AI model endpoints, LLM routing, usage tracking, cost awareness, and API integrations.
- Help manage internal knowledge systems using documents, code repositories, project management data, and other company sources.
- Evaluate new AI tools, frameworks, and workflows and determine whether they are practical, secure, and useful for the company.
- Communicate AI capabilities, limitations, and best practices to engineers and non-AI stakeholders.
- Work independently on ambiguous problems by researching, prototyping, using AI tools effectively, and turning ideas into working internal solutions.
- Help identify new areas across the company where AI, automation, or better tooling could reduce manual work or improve quality.
Requirements
- 2-3+ years of professional software engineering experience.
- Degree in Computer Science, Software Engineering, or a related technical field.
- Strong programming in Python and JavaScript/TypeScript, with ability to work across multiple languages and codebases given AI assistance.
- Experience building backend services, APIs, internal tools, or integrations.
- Experience with Docker, Linux server environments, and relational databases (PostgreSQL or similar).
- Strong curiosity about modern AI tools and a demonstrated habit of experimenting with new technologies independently.
- Ability to communicate clearly with engineers, managers, and other stakeholders.
- Personal AI projects, GitHub repos, demos, prototypes, or examples of independent experimentation., * Understanding of LLM systems including RAG architecture, embeddings, vector search, agents, retrieval quality evaluation, tool calling, and prompt engineering.
- Experience with on-premises AI platforms, local LLMs, RAG implementations, model routing, usage tracking, or controlled data environments.
- Familiarity with AI/automation tools such as OpenWebUI, Ollama, LiteLLM, n8n, vector databases, agent frameworks, or any of the many other tools.
- Experience with workflow automation platforms or building automated business/engineering workflows.
- Familiarity with CI/CD systems such as GitLab CI or GitHub Actions.
- Familiarity with web/backend frameworks (FastAPI, Flask, Express, Node.js, React).
- Experience building developer productivity tools, internal engineering platforms.
- Sound judgment about when to use AI and understanding of data security boundaries for sensitive, customer, or government-related data.