Principal Agentic Systems Architect
S&P Global2 days ago
Noida, India +2 moreStaff+
Responsibilities
- Define reference architectures and reusable design patterns for agent development, orchestration, tool calling, context management, multi-agent interaction, and human-in-the-loop controls.
- Set integration patterns for coding agents, agent frameworks, MCP servers, enterprise APIs, and security tools.
- Architect isolated, ephemeral execution environments with identity and access controls, secrets management, and full auditability.
- Establish standards for CI/CD, versioning, behavioral testing, agent evaluations, release management, and runtime operations.
- Define approaches for observability, failure handling, and production readiness across agent workloads.
- Guide engineering teams, review solution designs, evaluate technology choices, and resolve complex architectural challenges across initiatives.
- Validate architectural decisions through prototypes and proofs of concept with platform engineers and delivery teams.
- Document reusable patterns and standards across projects and teams.
Requirements
- 10+ years of experience in software engineering, solution architecture, or distributed systems.
- At least 2 years of experience building LLM or agent-based systems.
- Hands-on experience designing and building LLM-based applications, AI agents, or agentic workflows.
- Strong understanding of agent frameworks, coding agents, tool integration, MCP, and orchestration patterns.
- Cloud-native architecture experience with APIs, containers, Kubernetes, and distributed systems.
- Knowledge of application security, including IAM, secrets management, secure SDLC, and software supply-chain security.
- Experience with CI/CD, automated testing, observability, and production engineering practices.
- Strong programming skills in Python, Java, or Go sufficient to build working prototypes.
- Ability to make architectural decisions and influence multiple teams without direct authority.
- Experience in secure or regulated enterprise environments is preferred.
- Experience with enterprise coding-agent platforms such as Devin, GitHub Copilot agents, or Claude Code is preferred.
- Experience building secure, ephemeral execution environments, familiarity with agent evaluation frameworks and behavioral testing, and multi-cloud or multi-model-runtime integration experience are preferred.
Benefits
- Health care coverage and wellness benefits.
- Generous paid time off and flexible downtime.
- Continuous learning resources and career development opportunities.
- Competitive pay, retirement planning, continuing education support, company-matched student loan contributions, and financial wellness programs.
- Family-friendly benefits and perks.
- Retail discounts and referral incentive awards.
- Benefits vary by country.