Forward Deployment Engineer

TekWissen•Austin, TX

2d•Onsite

About The Position

TekWissen is a global workforce management provider headquartered in Ann Arbor, Michigan that offers strategic talent solutions to our clients world-wide. This role involves building and shipping AI agents and automation harnesses as a core deliverable, utilizing tool use/function calling, multi-turn context management, and agentic design patterns. The engineer will use Claude, Cursor, and Codex as their primary development environment, building with AI across every layer. A key aspect of the role is evaluating and correcting non-deterministic model output, understanding what the AI wrote, where it was overridden, and what would have shipped broken if trusted blindly. The engineer will take problems from rough idea to deployed, working software with minimal handoffs, writing code, shaping UX, and wiring data pipelines themselves, accelerated by AI tooling. They will design agents and internal AI-assisted workflows that other engineers will rely on. The role requires moving across frontend, backend, data engineering, and infra within the same sprint, using AI tools to compress the time each layer normally takes. Designing and maintaining data pipelines and analytical surfaces on Databricks and AWS that non-engineers can use is also a responsibility. The engineer will work directly with product managers and stakeholders, pushing back on scope, proposing better (often AI-driven) solutions, and making pragmatic trade-offs without waiting to be told. Owning architectural decisions for their product area, including when an agent/LLM-based approach is the right call versus deterministic code, is expected. The engineer should leave the codebase simpler than they found it, knowing when to abstract, inline, or simplify rather than add. Deploying, debugging, and operating confidently in AWS without breaking production is crucial. The goal is to deliver outcomes that would take a conventional team 5–10x longer, with the agentic/AI-native workflow being the primary driver of this multiplier, not just raw coding speed.

Requirements

AI Tooling: Claude, Cursor, Codex; LLM APIs (Anthropic, OpenAI); prompting, tool use, agent patterns, MCP
Frontend: React, TypeScript
Backend: Python or Node.js, REST/GraphQL APIs, event-driven service design
Data Engineering Databricks: (PySpark, Delta Lake, notebooks, workflows)
Cloud/Infra: AWS (S3, Lambda, Glue, Redshift)
React - Category: Technical - Category/Process: Scripting Language - Layer Sub Domain: presentation layer
Web Development Javascript Framework
Web Development, AWS
Python
Large Language Model (LLM)

Nice To Haves

Infrastructure-as-Code
BI/Visualization: Streamlit, Tableau, Evidence

Responsibilities

Build and ship AI agents and automation harnesses as a core deliverable using tool use/function calling, multi-turn context management, and agentic design patterns (MCP, LangChain-style frameworks).
Use Claude, Cursor, and Codex as primary development environment, building with AI across every layer.
Evaluate and correct non-deterministic model output as a first-class engineering discipline.
Take a problem from rough idea to deployed, working software with minimal handoffs, writing code, shaping UX, and wiring data pipelines yourself, accelerated by AI tooling.
Design agents and internal AI-assisted workflows that other engineers on the team rely on and build from.
Move across frontend, backend, data engineering, and infra within the same sprint, using AI tools to compress the time each layer normally takes.
Design and maintain data pipelines and analytical surfaces on Databricks and AWS that non-engineers can actually use.
Work directly with product managers and stakeholders, push back on scope, propose better (often AI-driven) solutions, and make pragmatic trade-offs without waiting to be told.
Own architectural decisions for your product area, including when an agent/LLM-based approach is the right call versus deterministic code.
Leave the codebase simpler than you found it, knowing when to abstract, inline, or simplify rather than add.
Deploy, debug, and operate confidently in AWS without breaking production.