AI Engineer, Agent Analytics & Optimization (DPI)

Conviva•Foster City, CA

5d•Hybrid

About The Position

Conviva is a leader in understanding and optimizing digital customer experiences through its Operational Data Platform, which captures comprehensive client-side telemetry to analyze customer experience and engagement across devices in real-time. The platform links user actions with service performance, providing AI-powered insights to technology, business, and operations teams. Trusted by major companies, Conviva transforms how businesses understand customer experience, maximizing satisfaction, conversion, and revenue by acting as the intelligence layer for digital businesses. This role focuses on building systems that enable AI agents to understand, query, and act on Conviva's behavioral data, including MCP servers, agentic workflows, and AI connectors. It is a hands-on builder role responsible for designing, shipping, and iterating on agentic systems from tool interface through deployment and observability, working closely with product and customers. This is a production-focused engineering role, not a research or prompt engineering position.

Requirements

3–7+ years of software engineering experience, with production systems shipped end-to-end.
Strong Python backend fundamentals; comfortable owning services from design through deployment.
Hands-on experience building and operating LLM-powered agents in production.
Practical familiarity with agentic patterns: tool use, structured outputs, prompt chaining, multi-agent coordination, and knowing when a deterministic workflow is appropriate.
Experience designing/building MCP servers or equivalent tool-use / AI connector integrations.
Have used evals to validate and debug agent behavior.
Comfortable with cloud deployment (GCP/AWS), containerized services, and async Python.
Strong product instinct — thinks about what users actually need and pushes back when a spec doesn't add up.

Nice To Haves

Fullstack experience is a plus.
Experience with agentic frameworks (LangGraph, Anthropic SDK, Pydantic-AI, CrewAI, or similar).
Experience with agent observability/tracing (Langfuse, LangSmith, OpenTelemetry, or homegrown).
Background in digital experience analytics, observability, or APM.
Familiarity with agent evaluation or LLM-ops tooling.
Published writing, talks, or open-source work at the intersection of engineering and AI.

Responsibilities

Design and build MCP servers that expose Conviva's data and analytics as discoverable, reliable tools for AI agents, with proper authentication, scoping, and access controls.
Architect and ship agentic workflows, including multi-step reasoning, tool use, orchestration patterns, and human-in-the-loop processes where necessary.
Develop AI connectors to integrate Conviva's intelligence with external agents, clients, and downstream systems.
Own the full lifecycle of agentic systems, including API/tool design, deployment, monitoring, and production hardening.
Use evals to validate agent behavior before shipping, catch regressions, and debug production divergence.
Build observability and tracing to make agent behavior inspectable and auditable.
Tune systems for latency, cost, and reliability as models and data drift.
Partner with Product Builders, design, and customers to ship working software.
Build internal SDKs, reusable patterns, and shared context to improve team efficiency.
Stay informed about the MCP/agent ecosystem and incorporate relevant advancements.