Senior/Staff Software Engineer, AI Agent Infrastructure

Responsibilities

• Build closed-loop measurement layer for agent workflows (acceptance, revert, override rates) to guide autonomy expansion.
• Advance autoresearch loop to unattended operation for bounded experiments, including evaluation and confidence machinery.
• Design isolation and permissioning models for agents acting on production repositories and infrastructure with full auditability.
• Develop agent-powered tooling across engineering lifecycle: code generation, review, debugging, test/CI failure attribution, knowledge retrieval, triage.
• Contribute to post-training of internal models where justified by workload.

Requirements

• 5+ years software engineering experience (or 4+ with Master's) in CS, engineering, or equivalent.
• Deep, current knowledge of LLM research: training from scratch, data, tokenization, architecture, pretraining, SFT, preference optimization, RL.
• Strong understanding of LLM inference: attention, KV-cache, batching, quantization, speculative decoding, prefix caching, context handling and tradeoffs.
• Experience building and operating production LLM-based agent systems (tool use, orchestration, sandboxing, retrieval, memory).
• Strong backend and distributed systems experience at scale: cloud infrastructure, service design, storage, queuing.
• Strong Python programming skills.
• Opinionated about evaluation and benchmarks.
• End-to-end ownership; ability to handle underspecified problems.
• Hands-on post-training/fine-tuning experience (SFT, preference optimization, RL, distillation) with associated evaluation.
• Experience with ML training/research infrastructure: experiment orchestration, evaluation pipelines, hyperparameter search, data pipelines.
• Experience running inference serving, cost, or capacity at scale.
• Familiarity with agent architectures: planning, reflection, long-horizon memory, multi-agent coordination.
• Experience with open tool-integration protocols, plugin/skill frameworks, model-routing/gateway layers.
• Background in developer experience, platform engineering, observability, or security isolation.

Nice-to-Haves

• Go, C++, or Rust experience in addition to Python.
• Staff-level candidates should demonstrate deeper scope and ownership.