SlipstreamJobs tracks this role from the company's public career site. Apply directly on the employer's site.
Forward Networks, founded in 2013 by Stanford Ph.D.s, is building the industry's first network digital twin—a mathematically accurate model of production networks that enables autonomous networking. The company serves global leaders including Goldman Sachs, PayPal, S&P Global, IBM, and Dell, helping them realize an average of $14.2 million in annual benefits. Backed by top-tier investors including Andreessen Horowitz and Goldman Sachs, Forward is headquartered in Santa Clara.
As an AI Engineer, you'll be at the forefront of building intelligent features that make enterprise networks smarter, more secure, and easier to manage. You'll work on the AI layer atop Forward's network digital twin, building and hardening agentic features and evaluation systems that keep them honest. Your work ships to some of the largest and most complex networks on the planet, where accuracy is mission-critical.
Key responsibilities include:
- Improve shipped agent quality through eval-driven iteration: error analysis on real trajectories, targeted fixes to prompts, context, and tools, and regression coverage
- Build new agent capabilities, tools, and surfaces with evaluations in place before shipping and quality metrics attached after
- Practice context engineering: retrieval, prompt and tool-result structure, and token-budget management against large, structured network models
- 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 network domain experts to build and validate evals
You should have 1-2 years of experience in the field, with a track record of personally owning and shipping at least one real feature on top of LLMs (agent, RAG system, or LLM-powered workflow). You think in terms of "how would we know it's better?" and enjoy debugging messy, real-world failures. You're proficient in one or more programming languages (Python, Java, C++, JavaScript) with solid software engineering fundamentals: clean, tested code, methodical debugging, and the ability to work with minimal supervision. You're comfortable getting productive in large, unfamiliar codebases and are a strong communicator and collaborator.
Nice-to-haves include experience with eval frameworks, LLM-as-judge, trajectory/error-analysis tooling, agent frameworks (LangChain, LlamaIndex), side projects or open-source work tracking the fast-moving AI field, and any networking, infrastructure, or systems background. Networking domain experience is not required but is a plus.
