Principal Engineer
Posted 32ds ago
Employment Information
Report this job
Job expired or something wrong with this job?
Job Description
Principal Engineer leading AI advancements across architecture, strategy, and hands-on development for S&P Global. Driving product and platform teams in modern AI practices and agentic workflows.
Responsibilities:
- Define reference architectures for agentic systems (single- and multi-agent patterns, planners, tool/skills frameworks, routing, memory, and long-running agents).
- Establish standards for agentic solutions: prompt/version management, evaluation, regression testing, observability, feedback loops, safety/guardrails, cost governance, and performance SLAs.
- Architect the end-to-end Agentic SDLC— including design principles, development workflows, evaluation pipelines, security/guardrails, deployment patterns, observability, governance, and continuous improvement practices for agentic applications and frameworks.
- Author clear, high-quality architecture decision records (ADRs), strategy papers, and reference implementations.
- Build production-ready agentic services and frameworks, including tool integrations (APIs, function calling), vector search, and workflow orchestration.
- Implement robust evaluation pipelines (offline/online), automated guardrails (content, privacy, bias), and telemetry (latency, quality, cost).
- Ship reusable SDKs, templates, and golden paths to accelerate teams adopting AI capabilities.
- Mentor senior/staff engineers; conduct design reviews; raise the bar for engineering excellence, documentation, and operational rigor.
- Ensure designs comply with security requirements; drive secure-by-default patterns.
- Champion AI literacy and agentic-first design thinking; run enablement workshops and internal demos; measure business impact and share wins.
Requirements:
- 10+ years in software engineering, including 5+ years in applied ML/AI or ML platform/LLMOps roles; proven track record as a Principal/Distinguished-level IC or equivalent scope.
- Expert in one or more language: Python, TypeScript, etc.
- Strong software design, testing, CI/CD, and observability skills.
- Deep experience with LLMs and agentic systems: tool/function calling, planning, memory, routing, multi-agent orchestration, and long-running workflows.
- Practical LLMOps: prompt management, offline/online evaluation, automated guardrails, dataset/versioning, data pipelines, human feedback, A/B tests, and cost/latency optimization.
- Cloud experience (preferably AWS)—including security, networking, identity, key management, and IaC (Terraform).
- Strong communicator with a history of producing clear architecture docs, diagrams, and decision records.
Benefits:
- Health & Wellness: Health care coverage designed for the mind and body.
- Flexible Downtime: Generous time off helps keep you energized for your time on.
- Continuous Learning: Access a wealth of resources to grow your career and learn valuable new skills.
- Invest in Your Future: Secure your financial future through competitive pay, retirement planning, a continuing education program with a company-matched student loan contribution, and financial wellness programs.
- Family Friendly Perks: It’s not just about you. S&P Global has perks for your partners and little ones, too, with some best-in class benefits for families.
- Beyond the Basics: From retail discounts to referral incentive awards—small perks can make a big difference.



















