AI Engineer: Eval-Driven Network Intelligence

Worky; Santa Clara (CA); On-site; USD 180,000 - 230,000; Full time

Benefits offered by this job

Competitive compensation

Benefits

Job summary

Forward is building the AI layer on top of the industry’s most accurate network digital twin, enabling engineers to reason over a precise model of production networks. As an AI Engineer, you’ll develop and harden agentic features and evaluation systems used by Fortune 500 networks.

This role favors builders who value evidence, with a focus on evals before opinions, and a love for tackling complex, high-signal AI challenges in a collaborative team.

Qualifications

• 1-2 years of experience in the field.
• Shipped at least one real feature on top of LLMs (agent, retrieval/RAG, or LLM-powered workflow).
• Experience debugging messy real-world failures and turning them into improvements.
• Proficiency in Python/Java/C++/JavaScript.
• Solid software engineering fundamentals: tested code and disciplined debugging.

Responsibilities

• Improve the quality of shipped agents through eval-driven iteration and error analysis.
• Build new agent capabilities, tools, and surfaces on the Forward platform with evaluation in place.
• Practice context engineering: retrieval, prompt and tool-result structure, token-budget management.
• Engineer prompts, tool descriptions, and instructions that are unambiguous and well-structured.
• Help define what “good” looks like for agents completing complex tasks end-to-end.
• Partner with domain experts to build and validate evals and share findings.

Skills

Python

Java

C++

JavaScript

LLMs

Eval frameworks

LangChain

LlamaIndex

Tools

tool-runner

Job description

Forward is building the AI layer on top of the industry’s most accurate network digital twin, enabling engineers to reason over a precise model of production networks. As an AI Engineer, you’ll develop and harden agentic features and evaluation systems used by Fortune 500 networks.

This role favors builders who value evidence, with a focus on evals before opinions, and a love for tackling complex, high-signal AI challenges in a collaborative team.