Software Engineer, Distributed Systems & AI Agents (Senior Level)

We are looking for a systems-minded engineer to build the distributed backend and execution infrastructure that powers AI agents. You will help build scalable, reliable, and secure systems at the intersection of distributed systems, agentic execution, and applied AI.

• →Take new ideas from 0-to-1 quickly, then evolve their architecture to scale by orders of magnitude—from early prototypes to production systems handling workloads that are 10×, 1,000×, or even 1,000,000× larger.
• →Build scalable distributed systems for large-scale unstructured-data extraction and agentic workloads.
• →Develop reliable execution infrastructure for scheduling, retries, timeouts, cancellation, rate limits, and failure recovery.
• →Build agent runtimes that coordinate model calls, tool execution, durable state, multi-step loops, and human approvals.
• →Evaluate emerging models and AI techniques through benchmarks and experiments, and apply them to new platform and customer problems.
• →Own systems from design through production, including testing, observability, and pragmatic trade-offs across reliability, performance, security, and cost.

• 5+ years of software engineering experience building and operating production backend systems, with the ability and experience toserve as a technical lead—setting direction, leading teams through complex projects, and mentoring and coaching engineers while remaining hands-on.
• Strong fundamentals in distributed systems, concurrency, APIs, data modeling, and failure handling.
• Experience with agentic execution systems, workflow orchestration, event processing, scheduling, or high-volume services.
• Proficiency in a backend language such as Python, Go, Java, Kotlin, Rust, or C++.
• Experience with queues, databases, caching, containers, cloud infrastructure, and production observability.
• Experience building or integrating ML, generative-AI, or LLM-based systems, including tool calling and agent workflows.
• A strong ownership mindset across design, deployment, monitoring, incident response, and continuous improvement.

Helpful experience: workflow engines or task executors; Kafka, Temporal, Celery, Ray, or similar systems; Kubernetes; agent runtimes, RAG, evaluations, model gateways, MCP, or AI observability.