Forward Deployed Engineer, Agentic Platform

Tkxel; Riyadh; On-site; SAR 300,000 - 500,000; Full time

Job summary

Tkxel in Riyadh seeks a Forward Deployed Engineer to shape how enterprises apply AI in real-world workflows. You will bridge our North product and client engineering teams, building agentic workflows powered by LLMs, with careful attention to reliability, observability, and security.

You will own end-to-end use cases, deploy RAG and agentic applications, work with data sources and tools, and travel up to 20-40% to sites.

Qualifications

• Hands-on experience building production-grade software in Python.
• Experience deploying RAG and agentic applications that plan and execute tasks.
• Familiarity with frontier models, vector databases, and orchestration frameworks.
• Ability to build robust evaluation frameworks measuring accuracy, safety, and latency.
• Experience communicating with enterprise stakeholders to translate needs into specs.

Responsibilities

• Design, build, and deliver LLM-powered agents across tools, APIs, and data sources.
• Lead end-to-end use cases from scoping to production.
• Collaborate with customers to translate problems into framed agentic workflows.
• Contribute to shared patterns for reliable, auditable enterprise delivery.
• Travel up to 20–40% to work on-site with customers and partners.

Skills

Python

LLMs

Agentic workflows

RAG

Evaluation frameworks

Customer engagement

Tools

Vector databases

Orchestration frameworks

Job description

Forward Deployed Engineer, Agentic Platform

Riyadh, Saudi Arabia | Posted on 09/04/2026

Tkxel is a leading softwaredevelopment company located in Reston, Virginia. We are committedto develop innovative software solutions for leading enterprisesin the world, helping them grow their businesses using latesttechnology solutions.

Job Description

This role offers a unique opportunity to shape how enterprises harness the power of AI in real-world applications. As a bridge between our core North product and our clients' engineering teams, you'll be at the forefront of solving complex problems and securely integrating AI into critical sectors such as finance, healthcare, and telecommunications.

We're looking for Software Engineers with Applied AI experience who can own the design, build, and deployment of agentic workflows powered by Large Language Models (LLMs), from early prototypes to production-grade AI agents, to deliver concrete business value in enterprise workflows. You'll work closely with customers on real-world business problems, often building first-of-their-kind agent workflows that integrate LLMs with tools, APIs, and data sources. While our pace is startup-fast, the bar is enterprise-high: agents must be reliable, observable, safe, and auditable from day one.

Work closely with our enterprise customers to translate high-value, ambiguous business problems into well-framed agentic workflows with clear success criteria and evaluation methodologies

Lead the design, build, and delivery of LLM-powered agents that reason, plan, and act across tools, APIs, and sensitive enterprise data sources, with enterprise-grade reliability and performance

Build and ship features for North, our AI workspace platform, working across the full product lifecycle from conceptualization through production

Take ownership of scoping and shaping use cases end-to-end, flexing into whatever technical area the problem demands (including frontend) to drive the most effective solution

Contribute to shared frameworks and patterns that enable consistent, high-quality delivery across customers and teams

Drive clarity in ambiguous situations, build alignment, and raise engineering quality across the organization

Travel up to 20-40% to work on-site with customers and partners

Requirements

You have hands‑on experience building and deploying production‑grade software in Python; you write clean, testable, observable, scalable code

You've built and deployed highly performant RAG and agentic applications, including agents that plan and execute multi‑step tasks using patterns like ReAct or Plan-and-Execute

You're deeply familiar with the LLM stack: frontier models, vector databases, and orchestration frameworks

You have a proven ability to build robust evaluation frameworks, moving well beyond trial and error, to measure agent accuracy, safety, and latency

You're experienced working directly with customers and can lead technical discussions with enterprise stakeholders, translating ambiguous business needs into concrete technical specs

You have experience owning the full scope of a use case end-to-end

You thrive in fast‑paced and ambiguous environments and can execute well even when priorities are shifting

It's a bonus if you have:

Experience setting architectural standards for AI and agentic systems across distributed teams

Experience flexing into unfamiliar technical areas, such as frontend, when the problem calls for it

Exposure to regulated or sensitive industry environments (finance, healthcare, telecoms)

Experience with enterprise security, compliance, or auditability requirements for AI systems