Internal AI Agent Engineer (Sales, Marketing, CS, and Ops)

PrescriberPoint

2h • $130,000 - $150,000 • Remote

About The Position

We’re rolling out AI agents that do real work across the organization—offloading administrative and operational tasks in Sales, Marketing, Customer Support, and Ops. We need a technical builder who can turn messy workflows and ambiguous goals into production agents people trust, integrated into the tools teams already use (CRM, support platforms, BI, knowledge bases, etc.).
This is not an R&D sandbox. You will be measured by what ships, reliability in production, adoption, and measurable operational impact.

Requirements

• 4+ years professional software engineering experience (backend, integrations, automation, platform).
• Production coding experience in Python and/or Node/TypeScript.
• Hands-on experience shipping containerized services with Docker (build, run, debug, deploy).
• Experience building AI-enabled applications (LLM apps, tool-using agents, or workflow automation) with a focus on reliability and evaluation.
• Strong testing and ops discipline: unit/integration tests, monitoring/logging, and incident response (formal or informal).
• Familiarity with agent SDKs/frameworks and orchestration patterns (e.g., OpenAI Agents SDK, Anthropic tooling, LangGraph/LangChain, workflow engines).
• Experience integrating with CRM/helpdesk/BI systems (e.g., Salesforce/HubSpot, Zendesk/Intercom, Looker/PowerBI/Snowflake).

Nice To Haves

• Experience building evaluation pipelines for LLM/agent quality (task success, groundedness, hallucination rate, escalation rate).
• Experience in regulated environments (healthcare/pharma) with auditability, data minimization, and access controls.
• Start up experience is always highly regarded

Responsibilities

• Workflow discovery → agent design → build → test → deploy → monitor → iterate
• Tool integrations (CRM/helpdesk/BI/docs/comms) with correct permissions, auditability, and resilience to change
• Quality + safety standards that prevent trust-breaking failures
• Production operations: evals, logging/traceability, dashboards, incident response, and regressions
• A repeatable “agent factory” (templates, shared skills, reusable connectors) that increases throughput without sacrificing quality
• Shadow functional teams, map workflows, and identify the highest-leverage admin tasks to automate.
• Turn those into a tight sequence of releases: MVP → v1 → v2.
• Implement agents using modern patterns: tool calling, retrieval/RAG, workflow orchestration, deterministic fallbacks, and (when justified) memory.
• Build agents that run both: Attended mode (human-in-the-loop approvals, confidence cues) Autonomous mode (policy-based execution, safe escalation, auditable actions)
• Write and maintain production code in Python and/or Node/TypeScript.
• Containerize agents/services with Docker, deploy to internal infrastructure, and manage configuration/secrets safely.
• Build robust connectors to business systems (CRM, ticketing, BI/warehouse, knowledge base, email/calendar) via APIs/webhooks/events.
• Design for reliability: idempotency, retries/backoff, rate limiting, timeouts, circuit breakers, and graceful degradation.
• Define and implement evals: golden sets, regression suites, scenario tests, offline replay, and launch checklists.
• Implement observability: structured logs, traces, tool-call auditing, failure clustering, and per-agent health dashboards.
• Triage production issues, run postmortems, and prevent repeat failures through tests and guardrails.
• Deliver workflow-native entry points (CRM buttons, ticket macros, Slack/Teams, internal UI).
• Document runbooks and “how to trust this” guidance based on real capability (no vapor).

Benefits

• 401(k) w/matching
• all kinds of insurance (including matching HSA and pets!)
• commute from your kitchen
• Open PTO (which leaders use!)
• remote stipend
• yearly education budget
• working with some of the smartest yet humblest and respectful people in the business

What This Job Offers

• Job Type: Full-time
• Career Level: Mid Level
• Education Level: No Education Listed