About the job
As an AI Software Engineer – Agentic AI System you will contribute to building infrastructure and tooling that supports an end-to-end evaluation ecosystem for agentic AI frameworks. This role is ideal for engineers who are eager to grow their skills across deployment, data, and AI systems while working closely with experienced engineers. This is a hands-on engineering role for individuals who enjoy learning new systems quickly, working across multiple layers of the stack, and contributing where the team needs them most.
Responsibilities
Build and maintain scalable deployment and orchestration systems for AI workloads
Develop data pipelines, dashboards, and observability tooling
Integrate and evaluate AI agent frameworks and model-serving systems
Design and automate evaluation pipelines for performance, reliability, and regression detection
Collaborate with global engineering teams to improve AI evaluation tooling
Qualifications
Minimum
Bachelor's degree (B.S. or B.A.) in Computer Science, Electrical Engineering, Mathematics, Statistics, or a STEM related
In addition, you must have 3+ years of experience in the following:
Software development experience
Experience with one of the languages Python/C++/TypeScript/RUST/Go
Containerized development with Docker, Linux, and command-line tooling
Experience with REST APIs and HTTP-based integrations
SQL (SQLite, PostgreSQL) for data querying
Experience with one of the following: AI agents, LLMs, or modern AI infrastructure
Preferred
Reading and navigating unfamiliar codebases quickly
Experience with CI/CD systems (GitHub Actions, Jenkins, or similar)
Experience with SSH, remote deployments, and multi-host orchestration
Familiarity with data visualization tools (Chart.js, D3, Grafana)
Experience with model serving tools (Ollama, llama.cpp, vLLM)
Experience with prompt engineering and LLM API integrations (such as Anthropic etc.)
Familiarity with messaging platform APIs (Telegram, Slack, Discord)
Experience with infrastructure-as-code or configuration management (Ansible, Terraform)
Experience with performance profiling (memory, CPU/GPU monitoring)
Contributions to or experience with open-source agent frameworks