Principal AI Engineer

What You’ll Do

Agent Harness & Flywheel Engineering

• Design and build agent harness infrastructure: the scaffolding that wraps LLM calls, manages tool use, handles retries, enforces policy, and feeds results back into iterative improvement loops.
• Implement agentic loop patterns with multi-turn reasoning, tool orchestration, memory management, and structured output handling as reusable platform primitives
• Build the agent flywheel: automated pipelines that collect agent traces, surface regressions, route failures to evaluation, and close the loop from production signal back to prompt/model improvement
• Own the end-to-end lifecycle from agent experiment to production deployment, including versioning, rollout controls, and rollback mechanisms

Sandboxing & Safe Execution

• Build sandboxed execution environments for agent tools with isolating code execution, API calls, and file system access so agents can act without unconstrained blast radius
• Design tiered autonomy models: define which actions agents can take automatically, which require human approval, and which are off-limits and enforced at the infrastructure layer
• Implement replay and dry-run capabilities so new agent versions can be tested against real traces before going live

Agent Evaluation, Observability & Optimization

• Implement evaluation frameworks for agent behavior using a combination of vendor, open source or in-house built tools — covering task success, tool selection accuracy, trajectory evaluation, hallucination rates, latency, and cost
• Build and maintain eval datasets, golden trace libraries, and regression test suites that run automatically on every agent code change
• Instrument agent traces end-to-end: LLM calls, tool invocations, intermediate reasoning, final outputs — surfaced in Grafana or equivalent observability tooling
• Define and track agent quality metrics over time; own the signal that tells the team whether agents are getting better or worse
• Drive continuous quality, latency, and cost improvements across deployed agents by closing the loop between production traces, evaluations, and agent design. Optimization may be done through prompt tuning, tool calling optimizations, context engineering, right-sizing model selection per task and explore distillation or fine-tuning (SFT, DPO, RLHF) on curated trace data to name a few
• Validate every optimization through A/B tests, shadow deployments, and replay against golden traces, with the eval suite gating rollout so wins are real and regressions are caught before they reach users

CI/CD & Workflow Automation

• Build and optimize CI/CD pipelines (Git Hub Actions, ArgoCD) that cover not just code deployment but agent evaluation gates — no agent ships without passing its eval suite
• Automate Docker and package builds, security scanning, and agent integration tests as first-class pipeline steps
• Design self-healing CI patterns where agent-based automation can diagnose and fix common pipeline failures

Tooling, Developer Experience & Architecture

• Build internal tools and developer self-service interfaces that let ML engineers and data scientists iterate on agents without platform team involvement
• Maintain a comprehensive view of how all platform components -> infrastructure, agent harnesses, evaluation pipelines, observability — work together
• Create architecture diagrams and drive long-term platform vision; own the "how does this scale to 10x" conversation

Monitoring, Security & Reliability

• Establish alerting (Grafana, Pager Duty) for both traditional platform health and agent-specific signals (error rates, tool call failures, eval score drift)
• Ensure all agent infrastructure adheres to security best practices: sandboxed execution, auditable traces, access controls on every tool
• Participate in security reviews; own compliance for agent workloads

• 9+ years as a Platform Engineer, ML Infrastructure Engineer, or Software Engineer
• Demonstrated experience building agent harness infrastructure using agentic loops, tool orchestration, structured output handling, multi-turn conversation management
• Hands-on experience with agent evaluation frameworks like Braintrust, Lang Smith, or equivalent, including…