AI Engineer

About the role

Founded in 2004, NetBrain is the leader in no-code network automation. Its Next-Gen platform enables IT operations teams to scale hybrid multi-cloud connected networks by automating diagnostic troubleshooting, outage prevention, and protected change management. Over 2,500 of the world’s largest enterprises and managed services providers use the platform. We are seeking a Senior AI Engineer to design and build production-grade agent and RAG systems that power intelligent, reliable automation across the platform.

Responsibilities

• Design and implement core capabilities for an enterprise‑grade Agent platform, including orchestration patterns (ReAct, Plan‑and‑Execute, Supervisor), tool execution, context and memory management, and safety guardrails.
• Design enterprise‑grade Agent execution and governance mechanisms, such as Human‑in‑the‑Loop approval workflows, multi‑tenant permission isolation, policy enforcement, and secure execution controls.
• Build reusable Agent Skills, standardized tool interfaces, and a scalable tool ecosystem integrated with NetBrain platform capabilities and business workflows.
• Design and implement LLM post‑training strategies: domain‑specific Supervised Fine‑Tuning (SFT), DPO/RLHF‑based preference alignment, parameter‑efficient fine‑tuning (LoRA) to improve model performance in network operations.
• Create an Agent self‑learning feedback loop that converts production execution traces, user feedback, and evaluation results into high‑quality datasets for continuously improving prompts, skills, models, and retrieval strategies.
• Analyze and optimize LLM behavior across instruction following, tool calling, structured output generation, contextual understanding, reasoning stability, and hallucination mitigation.
• Build production‑grade LLM and Agent evaluation frameworks and automated regression pipelines (benchmark datasets, deterministic checks, LLM‑as‑a‑Judge, tool‑call validation, retrieval‑quality evaluation, end‑to‑end task success metrics).
• Establish release quality gates and hallucination‑detection mechanisms for AI features to prevent accuracy, reliability, and performance regressions reaching production.
• Develop comprehensive AI system observability (distributed tracing, structured logging, metrics, dashboards, alerting) and rapidly diagnose/resolve production AI failures (hallucinations, incorrect tool selection, invalid parameters, Agent loops, retrieval degradation, structured‑output failures, latency regressions, unexpected model behavior changes).
• Design and implement highly reliable backend services for production AI and Agent workloads (asynchronous