Senior Agentic Systems Engineer
New
Fully remote work flexibility within the United StatesFull-TimeSenior
Salary124,800 - 156,000 USD per year
Apply NowOpens the employer's application page
Job Details
- Experience
- 5+ years
- Required Skills
- AWSPythonTerraformLLMGenerative AIDistributed Systems
Requirements
- Bachelor’s or Master’s degree in Computer Science or a related field
- 5+ years of production software engineering experience with strong focus on backend systems, platform engineering, or infrastructure
- Strong expertise in Python and building production-grade distributed systems
- Proven experience building AI agentic systems, including tool calling, multi-agent orchestration, or autonomous task execution
- Deep understanding of the generative AI ecosystem, including LLMs, orchestration frameworks, MCP, memory strategies, and execution sandboxing
- Hands-on experience with AWS, containerized services, and Infrastructure as Code (Terraform)
- Strong knowledge of security, isolation, and data protection in environments handling sensitive or regulated data
- Ability to clearly communicate technical tradeoffs to both technical and non-technical stakeholders
- Strong ownership mindset with ability to operate independently in ambiguous environments
Responsibilities
- Architect, build, and maintain AI agent orchestration platforms, including multi-agent systems, session management, and streaming interfaces for LLM-driven applications
- Design and implement Model Context Protocol (MCP) servers that expose domain capabilities as composable, reusable AI tools
- Develop secure and isolated execution environments, including sandboxed code execution, scoped permissions, HITL workflows, and tenant-aware data access controls
- Deploy and manage containerized services on AWS using Terraform, optimizing for performance, scalability, cost efficiency, and observability
- Integrate specialist AI agents across products by collaborating directly with ML, data, and product engineering teams without translation layers
- Own end-to-end delivery of technical solutions from concept to production, validating assumptions and closing system gaps proactively
- Diagnose and resolve complex distributed system issues across agent orchestration, infrastructure, and LLM providers using data-driven analysis
- Write high-quality, tested Python code with a strong focus on reliability, maintainability, and production readiness
View Full Description & ApplyYou'll be redirected to the employer's site
