Technical Delivery

Hebbia•New York, NY

12h•Onsite

About The Position

The Technical Delivery team is the engine behind bringing Hebbia to life within our customers' environments. We are builders, systems thinkers, and problem-solvers who translate customer needs into fully functioning AI-powered workflows. Sitting at the intersection of product, engineering, and go-to-market, the team is responsible for configuring, customizing, and deploying solutions that reflect how real teams operate - ensuring customers see value from Day 1. Role Overview Technical Delivery and AI Strategy operate as a two-person pod on every deployment. The AI Strategist owns the domain expertise and the customer relationship — they understand the workflow, the business problem, and the end-user deeply. Technical Delivery owns everything technical: the environment setup, the integrations, the AI architecture, and the build. Together, the pod is accountable for taking a customer from a signed contract to a live, confident, high-performing Hebbia deployment. You'll take true ownership of the technical delivery lifecycle across your assigned accounts. You'll configure Hebbia environments, assist in custom AI workflows and agent buildss, scope and execute integrations, and ensure customers are live and realizing value quickly. This structure means you won't be handed a spec sheet and told to execute - you'll be in the room, shaping the solution and taking real ownership from day one. You'll move fast, build things that matter, and directly see the impact of your work inside some of the world's leading financial institutions. This role is for someone who is technical, moves fast, and wants early ownership. You don't need 10 years of experience. You need intellectual curiosity, real hands-on technical ability, and the drive to figure things out in an environment that doesn't hand you all the answers. This role is based out of Hebbia’s New York City office in SoHo.

Requirements

2-5 years of experience in a technical implementation, solutions engineering, or engineering-adjacent role — you've shipped things in professional settings, not just in side projects
You have built and deployed LLM-powered workflows in a professional context — prompt engineering, agent frameworks, LLM orchestration, or AI automation are familiar territory
You've shipped real integrations: you're comfortable with REST APIs, authentication patterns (SSO/SAML/OAuth), and connecting systems that weren't designed to talk to each other
Strong command of structured data, configuration, and the technical building blocks of modern software stacks
You can take a loosely defined business problem and produce a working, production-quality solution with limited hand-holding
Clear, confident communicator — you can explain a technical architecture to a client's IT team in the morning and walk their end users through a workflow in the afternoon
High ownership orientation — you treat your accounts like they're yours, follow through completely, and don't drop threads
Thrives in ambiguity and moves with urgency in a fast-moving, high-expectations environment

Responsibilities

Own the technical delivery of Hebbia deployments end-to-end: from environment setup and SSO configuration through integration, workflow build, and go-live
Scope and execute integration projects, including identity/auth setup (SSO, SAML, OAuth), data connectivity, and API-based system integrations
Design and build customer-specific AI workflows, agents, matrices, and templates that reflect how real teams operate with support from AI Strategists and CoE
Lead prompt engineering, process engineering, and context engineering to optimize AI outputs for specific client use cases
Architect AI patchwork solutions that connect Hebbia's capabilities to customer data environments and adjacent tools
Partner closely with your paired AI Strategist to translate business requirements into working technical systems
Surface patterns, edge cases, and product feedback to Engineering and Product — you are a first-line signal for what customers actually encounter
Build repeatable playbooks, deployment templates, and reusable components that improve speed and quality across future deployments
Document technical configurations, integration patterns, and best practices to grow the team's collective knowledge base