Define the golden path so any employee-experience squad can ship a safe, evaluated agent in weeks — not quarters.
Flagship employee-experience agents
Ship agents that measurably deflect / auto-resolve high-volume employee journeys, e.g. IT service desk incidents, access & entitlements.
Design multi-agent and human-in-the-loop patterns that know when to act, when to draft, and when to escalate.
Instrument every agent with business KPIs (deflection rate, time-to-resolve, CSAT, cost per interaction) and quality KPIs .
Reliability, safety, and controls
Establish SRE for agents: SLOs, error budgets, canaries, circuit breakers, prompt/model version pinning, deterministic replay, rollback.
Partner with cybersecurity, privacy, model risk, controls, and audit to make responsible AI concrete: data minimization, purpose limitation, PII handling, evaluation before change, model & prompt inventory, drift detection, red-teaming, jailbreak defense, secret and tool-use hygiene.
Own the evaluation harness: offline benchmarks, online A/B, gold sets, LLM-as-judge with human calibration, regression gates in CI/CD.
Delivery leadership
Lead squads via principal/lead engineers; set the technical bar via architecture reviews, code quality standards, and design docs.
Grow senior Italent (staff / principal); run a strong hiring bar; sponsor diverse talent.
Business partnership
Communicate crisply to Managing Directors and executive stakeholders — trade-offs, risks, timelines, and results.
Required qualifications, capabilities and skills
12+ years of software engineering experience, including 5+ years leading engineers and 3+ years shipping production ML/AI (with at least 1+ year shipping LLM- or agent-based systems to real users).
Deep hands-on expertise in at least one modern language (Python, TypeScript, Java, Go) and comfort operating polyglot codebases.
Track record of designing and running large-scale distributed systems in production (SLOs, on-call, incident command, cost).
Practical experience with the agentic stack: LLM orchestration (e.g. LangGraph, LlamaIndex, Semantic Kernel, custom), tool/function calling, RAG, evaluation harnesses, guardrails, prompt & model versioning, model gateways. Hands-on with Model Context Protocol (MCP) architectures — designing servers/clients, tool schemas, capability negotiation, and secure enterprise deployment patterns.
Strong grounding in data platforms (Databricks / Snowflake / lakehouse patterns), event streaming, and modern MLOps/LLMOps (CI/CD, feature/prompt/model registry, observability).
Proven leadership in responsible AI, security, and controls for enterprise deployments: PII/PCI/PHI handling, model risk, red-teaming, jailbreak & prompt-injection defense, secret & tool-use hygiene.
Executive-level communication: you can move fluently between a whiteboard architecture, a code review, and a conversation with a Managing Director.
Bachelor's in Computer Science or related discipline, or equivalent industry experience.
Preferred qualifications, capabilities and skills
Experience building employee-facing products at scale (IT service desk, HR tech, knowledge management, workplace assistants).
Experience integrating with different data sources, ServiceNow, identity providers, endpoint management, and enterprise search.
Experience with multi-agent patterns (planner-executor, supervisor-worker, debate/critique) and long-horizon workflows.
Contributions to open source, published research, patents, or public talks in AI/agents/SRE.
Prior experience in a highly regulated environment (financial services, healthcare, public sector) with model risk management (SR 11-7 or equivalent).
Master's or PhD in a quantitative discipline.