Staff Software Engineer-AI
Salary not listed • Hyderabad • Full-time
Posted 4mo ago
This job has been open for more than 60 days. It may no longer be actively hiring, so check with the company before putting a lot into an application.
About the job
DigitalOcean's Agentic AI organization is seeking a Staff Software Engineer to provide technical leadership for their Feedback Systems team. This role will focus on architecting massive-scale infrastructure for simulating, testing, and evaluating AI agents. You will define the architectural vision for systems that simulate multi-agent, multi-turn deployments with tool integration, enabling customers to analyze "what-if" scenarios for their AI agents. This is a high-impact leadership position involving advanced problem-solving at the intersection of LLM orchestration, synthetic data generation, and behavioral simulation, including defining user personas and structuring evaluation objectives. You will set technical standards and guide engineering strategy across the Agentic AI organization.
Responsibilities
- Lead the design and implementation of multi-agent, multi-turn simulation environments where synthetic users and AI agents interact dynamically and leverage tools.
- Design ML pipelines to analyze user conversations and synthesize realistic user personas and simulation goals.
- Build core methodology and scoring infrastructure for customers to run alternative configuration scenarios and benchmark agent behavior.
- Lead the design and architecture of high-throughput, stateful workflow orchestration systems for AI agent simulations.
- Define robust API contracts and system boundaries for integrating telemetry data, simulation engines, and remote execution environments.
- Drive the technical roadmap for the Feedback Systems team, balancing scalability with product delivery.
- Design solutions for distributed systems challenges like rate limiting, backpressure, and state management.
- Mentor senior engineers, lead architectural reviews, and establish engineering best practices.
- Design and implement backend infrastructure for evaluation engines, integrating with LLMs and agentic workflows.
- Act as a technical bridge across the Agentic AI organization, partnering with Product Managers and engineering leaders.
Requirements
- 5+ years of software engineering experience with deep proficiency in modern AI/ML frameworks and LLM orchestration (e.g., LangChain, AutoGen, CrewAI, or custom multi-agent frameworks).
- Production-grade Python and Go experience.
- Background in processing natural language data to extract user intent, synthesize personas, and generate simulation goals.
- Solid experience building evaluation frameworks for non-deterministic AI systems, including metrics, guardrails, and scoring rubrics.
- Strong understanding of managing complex state in asynchronous architectures, streaming LLM tokens, and handling rate limits.
- Experience manipulating heavy data pipelines to feed simulation engines.
- 10+ years of software engineering experience, with a proven track record at Staff, Principal, or Architect level designing mission-critical distributed systems.
- Expert-level understanding of designing highly concurrent, fault-tolerant, and globally scalable backend architectures.
- Deep architectural experience with stateful, durable workflow orchestration engines.
- Extensive experience designing resilient, high-performance APIs (e.g., gRPC) and managing high-throughput message/event-driven architectures.