Embedded AI Engineer for Logistics Solutions

Speak to Kit; Chicago (IL); Híbrido; USD 116.000 - 181.000; Jornada completa

Descripción de la vacante

Speak to Kit is seeking a Forward Deployed Engineer in Chicago for a full-time, hybrid role. You’ll spend roughly 50% of your time embedded at client sites across the US, shadowing operations to uncover real problems and ship AI-driven solutions with speed and rigor.

You’ll wire together LLM agents, REST APIs, and enterprise systems, design end-to-end automations, and collaborate with a senior strategist to earn trust in the client ops room before you write code.

Formación

• 5+ years full-stack engineering experience.
• Strong Python and TypeScript, including fast-prototyping frameworks.
• Hands-on production experience with LLM agent workflows, RAG pipelines, and model integrations.
• LLM evals, observability, latency optimisation, and cost management in live products.
• Comfort wiring REST and GraphQL APIs, webhooks, and enterprise systems.
• Proven ability to translate operational problems into technical solutions for non-technical stakeholders.
• Track record of shipping working software quickly in ambiguous, fast-changing environments.
• Ability to debug, re-scope, or improvise in front of a client without escalating and waiting.
• Willingness to travel approximately 50% of the time, embedded at client sites across the US.

Responsabilidades

• Shadow client operations teams to observe workflows firsthand, then run structured discovery to identify and prioritise the pain points worth solving.
• Design the right solution for each prioritised problem, whether that's an AI agent, an automation, a system integration, or a combination, and scope it before building.
• Build and integrate solutions against real enterprise systems, including TMS, WMS, WMS, and ERP platforms.
• Prototype and ship working automations, such as shipment tracking flows, carrier onboarding, and voice or chat-based agents, prioritising speed to value.
• Tune prompts, agent behaviour, and transcription models based on real production data and edge cases, and keep refining after launch as usage surfaces new ones.
• Identify security, compliance, and infrastructure requirements early, and resolve them with internal stakeholders before they become blockers.
• Feed recurring patterns back to product and engineering, turning one-off client solutions into reusable platform capabilities.
• Use agentic coding tools daily to amplify output while owning every line that ships.

Conocimientos

Full-stack engineering

Python

TypeScript

LLM agent workflows

RAG pipelines

REST & GraphQL

client-facing

ambiguous environments

Herramientas

LLM agents

enterprise systems

Descripción del empleo

Speak to Kit is seeking a Forward Deployed Engineer in Chicago for a full-time, hybrid role. You’ll spend roughly 50% of your time embedded at client sites across the US, shadowing operations to uncover real problems and ship AI-driven solutions with speed and rigor.

You’ll wire together LLM agents, REST APIs, and enterprise systems, design end-to-end automations, and collaborate with a senior strategist to earn trust in the client ops room before you write code.