Описание

This role exists to build systems that generate pipeline for Incode, focusing on the top of the funnel. You will design and ship new AI agents, harden existing ones, and own the integration layer connecting them to revenue systems. This is applied engineering measured by qualified pipeline, meetings held, and hours returned to the revenue team, not internal-tools ticket queue or research.

Responsibilities

Design, build, and ship production LLM agents that generate and qualify pipeline, including scoped skills, explicit guardrails, human-in-the-loop checkpoints, and clean multi-agent handoffs
Take agents from concept to daily use by non-technical operators across outbound, inbound, and event motions
Build and operate Model Context Protocol servers and clients that connect agents to Salesforce, Outreach, Supabase, ZoomInfo, Notion, and Slack
Own authentication, token scoping, pagination, rate limiting, and graceful failure for integrations
Build schema-aware retrieval, reconciliation checks, eval harnesses, and regression tests to ensure agent output is tied to real records
Implement routing, scoring, and trigger logic across automation platforms (n8n, Tines-class) and custom services
Build web apps, dashboards, and interactive reporting to present agent output to BDRs and leadership
Write runbooks, skill specifications, and architecture docs to make the agent fleet maintainable
Enable GTM operators to extend what you build without filing a ticket

Requirements

4+ years of professional software engineering experience
1+ year building and shipping LLM-powered applications or agents to production, used daily by non-engineers
Strong Python and Node.js/TypeScript in production
React sufficient to build internal UI end to end
Built at least one internal application start to finish: data model, backend, interface, auth, deployment, and maintenance
Hands-on experience with both Salesforce and HubSpot, including standard and custom objects, field behavior, record ownership, APIs, and understanding of downstream impacts
Sales engagement platform experience (Outreach, Salesloft, or Apollo): sequence and step models, prospect and mailing data structures, and API access patterns
Realistic view of how revenue data degrades in practice and its implications for automation
Production experience with Postgres or Supabase: schema design, migrations, indexing, query tuning, row-level security
SQL fluency against a warehouse (Redshift, Snowflake, or BigQuery-class), including window functions and incremental models
Reconciled metrics across two systems, found deltas, and explained them to non-technical stakeholders
Designed, built, deployed, monitored, and maintained automations in production, owning alerting and failure modes
Experience with webhooks, queues, scheduled jobs, retries, idempotency, and backfills, and debugging jobs that silently stopped firing
Automation platform experience (n8n, Tines, Zapier-class) and judgment to know when to abandon the platform for custom service
Implemented routing, scoring, and decision logic as code with test coverage
Hands-on with MCP (Model Context Protocol) servers, clients, custom endpoints, or equivalent tool-calling and agent framework
Production LLM API integration (Anthropic-class): structured output, tool definitions, context management, cost and latency tradeoffs
Prompt and skill design treated as versioned artifacts, with a method for evaluating changes
Cloud deployment ownership: AWS, containerized hosting, CI/CD (GitHub Actions)
Experience with OAuth flows, token lifecycle and refresh, credential vaults, header auth, and least-privilege scope review on integrations

Nice to have

Experience supporting a multi-region revenue team (NAM, LATAM, EMEA) and associated data-residency questions
Event and conference lead-capture tooling
Notion and Slack API work
Experience enabling non-technical teams on AI tooling: documentation, training, internal adoption
Terraform or another IaC tool

We offer

$105,000-$175,000 annual salary
Full-time employment
Flexible working hours and workplace
Open vacation policy

Hiring process

Come ready to walk us through two or three things you have built, such as an internal application, a two-way integration, an agent/automation replacing a manual process, a data reconciliation, or something you built, documented, and handed off.