Senior Software Engineer
Builds AI-native developer tooling, agentic workflows, and CI/CD automation that improve engineering velocity and software delivery. The role requires 4+ years of software engineering experience, infrastructure or internal tooling expertise, and production experience with LLM-powered systems.
About the job
Responsibilities
- Design and ship AI-native tooling and agentic workflows that accelerate how engineers build, ship, and operate software.
- Build tools, systems, and processes that increase engineering velocity, reduce manual effort, and improve software delivery quality.
- Use LLM APIs, agentic workflows, MCP patterns, and AI-assisted development environments to improve engineering productivity.
- Architect and operate multi-step agentic systems with defined inputs, outputs, validation checkpoints, and human-in-the-loop guardrails.
- Integrate AI-assisted capabilities into CI/CD pipelines and GitHub Actions workflows to improve build reliability, code-quality feedback, and developer toil reduction.
- Advise product engineering teams on building observable, scalable systems.
- Identify high-friction engineering workflows, translate them into AI-assisted automation, and measure impact against success metrics.
- Instrument AI-powered features with logging, monitoring, evaluation, and lifecycle management.
- Document patterns, usage guidance, and best practices for organization-wide adoption.
Requirements
- 4+ years of professional software engineering experience, including 3+ years building infrastructure or internal tooling for developer teams.
- Fluency in Python or Go.
- Firsthand experience with software engineering tools, workflows, and pain points.
- Experience building and deploying agentic or LLM-powered systems in production.
- Familiarity with MCP patterns, tool-augmented workflows, or multi-step agent architectures.
- Experience integrating LLM APIs such as Anthropic Claude or OpenAI, including understanding of context management, latency, cost, and safety tradeoffs.
- Experience with GitHub Actions or similar CI/CD platforms, including custom workflows, reusable actions, or code and pull-request automation.
- Daily use of AI-assisted development tools such as Cursor, Claude Code, or Copilot.
- Ability to define metrics for AI-assisted tooling and run time-bound experiments.
- Clear written and verbal communication skills, with the ability to advise and influence distributed engineering teams.
Benefits and Compensation
- Healthcare benefits.
- Internet and cell phone reimbursement.
- Learning and development stipend.
- Potential opportunities to travel to the Mountain View headquarters.
- Salary ranges are determined by role, level, and location.
- Visa sponsorship and immigration support are not available.
Skills
Python, Go, LLM APIs, Mcp, Agentic Workflows, GitHub Actions, CI/CD, Anthropic Claude, OpenAI, Cursor, Claude Code, GitHub, Monitoring, Logging, Evaluation
Similar jobs
DevOps / SRE jobsThe Senior Network Engineer will design, automate, and operate large-scale, high-performance network infrastructure for AI data centers and GPU clusters. The role requires 5+ years of data center networking experience, expertise in spine-leaf fabrics and routing protocols, and familiarity with HPC or GPU-dense environments.
The Production Engineer will build and operate secure, scalable, and reliable infrastructure and production services, while developing engineering frameworks and supporting on-call operations. The role requires 5+ years of production, site reliability, or DevOps experience and familiarity with AWS, Kubernetes, and Terraform.
Designs and operates scalable, highly available cloud infrastructure while leading efficiency initiatives across compute, storage, networking, and cost optimization. Requires 5+ years of distributed-systems software development experience and expertise with cloud platforms, infrastructure as code, and Kubernetes.
Build and optimize ClickHouse Cloud’s highly available, multi-cloud infrastructure, including automation, distributed systems, networking, security, and cost-efficiency tooling. Requires 5+ years of experience operating scalable systems and expertise in cloud platforms, infrastructure as code, and production engineering.
Build and operate cloud infrastructure, Kubernetes platforms, CI/CD systems, and observability for exabyte-scale data systems and reliable enterprise AI workloads. The role requires 5+ years of infrastructure, platform, or distributed systems experience and strong programming and cloud skills.