AI Engineer
Build secure infrastructure, control planes, developer tools, and observability for production AI agents. The role requires 6+ years of software engineering experience, strong Python and backend expertise, AWS, distributed systems, AI agent development, and security engineering experience.
About the job
Responsibilities
- Design and build secure AI infrastructure for production AI agents.
- Develop Agent Control Plane capabilities to manage, monitor, and secure agent execution.
- Build embedded controls and security mechanisms into AI agents.
- Develop reusable services, APIs, and developer tooling for AI applications.
- Build and maintain integrations with Agent SDKs and Model Context Protocol (MCP).
- Design backend microservices using Python and AWS.
- Build observability into AI systems, including telemetry, monitoring, tracing, and operational visibility.
- Develop public-facing developer tools and command-line interfaces (CLI).
- Partner with AI researchers to transition prototypes into production-ready systems.
- Own projects from architecture through deployment.
- Help define engineering standards and reusable patterns across the AI platform.
- Collaborate with senior engineers and independently lead technical initiatives.
Requirements
- 6+ years of professional software engineering experience.
- Strong backend engineering background.
- Excellent Python development experience.
- Experience building backend services and microservice architectures.
- Experience with AWS cloud services.
- Experience designing APIs and distributed systems.
- Hands-on experience building AI applications, AI agents, or agentic workflows.
- Experience working with Agent SDKs.
- Familiarity with Model Context Protocol (MCP).
- Experience building developer tools, APIs, or CLI applications.
- Strong understanding of software architecture and production engineering.
- Comfort working in startup environments with significant ownership.
- Ability to drive projects independently from concept through production.
- Security engineering background.
Nice-to-haves
- Experience building Agent Control Planes.
- Experience implementing embedded controls or policy enforcement within AI agents.
- Experience building AI observability platforms.
- Infrastructure engineering background.
- Experience building secure AI systems.
- Experience working with LLMs in production environments.
- Experience with Kubernetes and containerized services.
- Experience integrating AI systems with cloud infrastructure.
Compensation and Benefits
- Comprehensive health benefits.
- Discretionary time off.
- Paid holidays, including monthly personal days.
- Inclusive and diverse workplace.
Skills
Python, AWS, Microservices, APIs, Distributed Systems, AI Agents, Agent Sdks, Model Context Protocol, Cli, Kubernetes, Docker, LLMs, Telemetry, Monitoring, Tracing
Similar jobs
AI Research jobsBuild Vanta’s organizational intelligence layer by shipping prototypes, internal tools, and AI agent workflows that make cross-source data useful to EPD, GTM, and other teams. The role requires recent hands-on LLM product work, independent problem scoping, and strong judgment around AI quality, reliability, cost, and latency.
Conduct applied research on AI agents, designing experiments and evaluation systems to improve reliability, context retention, and multi-step task completion. The role requires strong AI/ML research, engineering, experimental design, and communication skills.
Conducts deep technical research into cloud- and AI-native environments to identify novel risks and attack vectors, then translates findings into product capabilities with Product and Engineering teams. Requires at least five years of security research experience and strong scripting and telemetry-analysis skills.
Conduct research on long-horizon, multi-agent AI behavior by designing agent environments, analyzing large-scale data, and running experiments. The role requires strong research judgment, rapid execution, independence, and familiarity with current AI developments.
Build, optimize, and evaluate long-running and multi-agent AI systems, along with tools for monitoring and analyzing their real-world behavior. The role requires software engineering experience with coding agents, strong independence, and familiarity with current AI developments.