Software Engineer, Agentic Platform - TikTok USDS

Responsibilities

The Agentic Platform team is the force‑multiplier for Tik Tok USDS JV's Infrastructure and Platform teams. We are building and deploying a highly advanced, autonomous layer of AI agents that act as "virtual team members" for SRE, Systems, Capacity, Networking and operational roles. Our agents don’t just alert—they observe signals, diagnose root causes, execute complex machine remediations, and safely report outcomes to humans and core cloud infrastructure.

Operating under the principle that "agents own the toil, humans own the judgment," we are a 0 to 1 engineering team tackling massive infrastructure challenges. Over the next 6 months, our mission is to eliminate over 50% of manual ticket‑handling effort across USDS and measurably optimize critical machine infrastructure (GPU, HDFS) and Disaster Recovery (DR) readiness metrics.

• Design, build, and deploy production‑grade, highly concurrent services that form the core of the Agentic Platform runtime, tool registry and integrations.
• Apply the Agentic Platform to specific workflows, scaling diagnostic playbooks and enabling intelligent triage, isolation, and auto‑healing of complex hardware and system faults (e.g., FS read‑only, disk, RDMA, and network interface cards).
• Integrate our AI agent framework with core internal logging, monitoring, and ticketing systems (e.g., SAOS, Fault, Tianshu, and Alto).
• Embed telemetry, monitoring, and metrics into every agent to track throughput, fault rates, and time‑to‑remediation, ensuring highly visible platform performance.
• Maintain robust automated testing and CI/CD pipelines to deploy agents safely into production under strict compliance and data‑boundary guardrails.

• BS/MS degree in Computer Science, Computer Engineering, or a related technical discipline with industry experience.
• 2+ years of experience as a software engineer with proven contributions to team‑based projects, ideally in an infrastructure, automation, or backend platform role.
• Solid programming skills, with deep proficiency in Python, Go, or C/C++ and a strong grasp of data structures and algorithms.
• Experience building and maintaining RESTful APIs, microservices, or backend automation workflows.
• Exposure to or strong interest in LLM orchestration, custom agent architectures, or API‑driven automation.
• Basic understanding of Linux internals, telemetry pipelines (logging/metrics), and SRE concepts like MTTR and fault isolation.
• Knowledge of concurrent programming and distributed systems design.

On‑site presence across teams allows the company to operate with greater speed, alignment, and agility. Accordingly, the company is shifting from a hybrid work model to a fully in‑person schedule up to 5 days a week.

USDS is committed to providing reasonable accommodations in our recruitment processes for candidates with disabilities, pregnancy, sincerely held religious beliefs or other reasons protected by applicable laws. If you need assistance or a reasonable accommodation, please reach out to us at

【For Pay Transparency】Compensation Description (Annually)
The base salary range for this position in the selected city is $136,800 - $259,200 annually.
Compensation may vary outside of this range depending on a number of factors, including a candidate’s qualifications, skills, competencies and experience, and location. Base pay is one part of the Total Package that is provided to compensate and recognize employees for their work, and this role may be eligible for additional discretionary bonuses/incentives, and restricted stock units.
Benefits may vary depending on the nature of employment and the country work location. Employees have day one access to medical, dental, and vision insurance, a 401(k) savings plan with company match, paid parental leave, short‑term and long‑term disability coverage, life insurance, wellbeing benefits, among others. Employees also receive 10 paid holidays per year, 10 paid sick days per year and 17 days of Paid Personal Time (prorated upon hire with increasing accruals by tenure).
The Company reserves the right to modify or change these…