Description
Are you a hands-on engineer who wants to build AI agents that do real work? Not demos, but agents that provision infrastructure, investigate incidents, answer the questions engineers would otherwise file a ticket for, and take action safely on production systems?
Our technology organization runs the cloud, compute, and network platforms that thousands of engineers across Thomson Reuters build on, spanning AWS, Azure, and our own data centers. We are rethinking how that platform is built and operated, with AI agents and automation taking on work that used to require tickets, runbooks, and manual toil. We are looking for a Staff Software Engineer to help lead that work.
Key Responsibilities
- Design and build AI agents that reason over context, call tools, and take action on real systems, from single-purpose assistants to multi-step workflows with human approval where it matters.
- Build the APIs, MCP servers, and integrations that give agents safe, well-scoped access to cloud providers, source control, service management, observability, and internal platforms.
- Build infrastructure-as-code, pipelines, and self-service capabilities that let engineers get what they need without waiting on a person.
- Own production-grade concerns for agents, including evaluation and regression testing, observability, cost and latency management, guardrails, least-privilege access, defenses against prompt injection, and auditability.
- Lead technically by owning the design of major systems, writing clear design documents, leading design and code reviews, establishing reusable patterns and standards, and mentoring engineers across the team.
- Apply judgment about when AI fits, recognizing when a deterministic script, a better API, or a process change is the right answer and making that case clearly.
- Partner with platform, cloud, security, and SRE teams, and with the stakeholders whose work is being automated, to turn ambiguous problems into well-defined solutions.
Required Qualifications
- 6+ years of professional software engineering experience, including designing, building, and operating production systems.
- Strong proficiency in at least one modern programming language. Python is the primary language and experience with it is a plus, but strong engineers from Go, TypeScript, C#, Java, or similar backgrounds who are ready to work in Python are welcome.
- Hands-on experience building applications or agents on large language models, including tool and function calling, context management, retrieval (RAG), and structured outputs, with a practical understanding of failure modes such as hallucination, non-determinism, and prompt injection.
- Experience with AWS and/or Azure and with infrastructure-as-code tools such as Terraform, AWS CDK, CloudFormation, or Bicep.
- Experience with modern delivery practices, including Git-based workflows, CI/CD (e.g., GitHub Actions, Azure Pipelines), automated testing, and containers.
- A secure-by-design mindset, especially when giving software the ability to act on production systems.
- Clear written and verbal communication, including the ability to write a strong design document and explain complex trade-offs to technical and non-technical audiences.
- A track record of technical leadership, including mentoring engineers, leading through influence, and raising the quality of a team’s work.
- Bachelor’s degree in Computer Science or a related field, or an equivalent combination of education and experience.
Preferred Qualifications
- Experience with the Model Context Protocol (MCP) or agent frameworks and SDKs such as LangGraph, the Claude Agent SDK, OpenAI Agents SDK, Microsoft Agent Framework, or Amazon Bedrock AgentCore.
- Experience designing evaluation suites for LLM systems, or with LLM observability tooling (e.g., OpenTelemetry, Langfuse, LangSmith).
- Experience with Kubernetes, serverless architectures, or event-driven systems.
- Background in platform engineering, SRE, or DevOps, including on-call and incident response.
- Familiarity with networking fundamentals (DNS, firewalls, cloud networking) or IT service management platforms such as ServiceNow.
- Experience working in large, regulated, or compliance-conscious enterprise environments.
What’s in it For You?
- Hybrid Work Model: We’ve adopted a flexible hybrid working environment for our office-based roles while delivering a seamless experience that is digitally and physically connected.
- Flexibility & Work-Life Balance: Flex My Way is a set of supportive workplace policies designed to help manage personal and professional responsibilities, whether caring for family, giving back to the community, or finding time to refresh and reset.
- Career Development and Growth: By fostering a culture of continuous learning and skill development, we prepare our talent to tackle tomorrow’s challenges and deliver real-world solutions.
- Industry Competitive Benefits: We offer comprehensive benefit plans to include flexible vacation, two company-wide Mental Health Days off, access to the Headspace app, retirement savings, tuition reimbursement, employee incentive programs, and resources for mental, physical, and financial wellbeing.
- Culture: Globally recognized, award-winning reputation for inclusion and belonging, flexibility, work-life balance, and more.
- Social Impact: Make an impact in your community with our Social Impact Institute.