Forward Deployment Engineer

Mackinnon Bruce International; Dallas (TX); On-site; USD 198,000 - 242,000; Full time

Job summary

Mackinnon Bruce International is seeking a Forward Deployment Engineer to anchor an on-site agentic AI initiative in Dallas, translating business intent into scalable, production-grade systems. You will govern end-to-end architectures across customer platforms, while leading delivery teams and engaging with executives.

This role requires hands-on coding, code reviews, and fast trade-off decisions, with extensive experience in AI/GenAI production and onshore/offshore delivery.

Qualifications

• Extensive enterprise/platform architecture experience.
• Production delivery of AI/GenAI systems in an enterprise.
• Hands-on with agent frameworks and Python proficiency.
• Strong API design, distributed systems and real-time data expertise.
• Experience leading onshore and offshore delivery models.
• Ability to define guardrails, governance and MSCP standards.

Responsibilities

• Design and govern end-to-end agentic architecture for customer digital experiences.
• Architect multi-agent orchestration patterns and tool calling.
• Define run-time guardrails, spend controls, and audit trails.
• Lead integration of AI agents with energy systems like billing and metering.
• Set LLMOps standards including prompt versioning and observability.
• Bridge business leaders, delivery teams and platform partners.
• Provide technical leadership onshore in Dallas, TX.

Skills

Enterprise architecture

API design

Distributed systems

Real-time data

AI/GenAI production

LLM agent systems

Python proficiency

Executive credibility

Onshore/offshore delivery

Tools

LangGraph

LangChain

Semantic Kernel

CrewAI

AutoGen

LangSmith

Langfuse

Kafka

Job description

Forward Deployment Engineer, Agentic AI and Digital Platforms

MBI are currently partnered with a global digital transformation and data consultancy that is building agentic AI into the customer facing digital platforms of leading energy and utilities businesses. With a growing program of work and a clear need for senior technical leadership on the ground, they are looking for an architect who can turn ambition into production systems.

Have you shipped agentic AI into production, or only demoed it?

If you have spent years architecting enterprise platforms and now build LLM based agent systems that survive real traffic, real customers and real governance, this could be the opportunity you have been looking for. Our client does not need a slide deck architect or a researcher. They need someone who writes code, reviews code and debates trade offs in the same week they brief a VP.

The Role

Based onsite in Dallas, Texas, you will be the onshore technical anchor for an agentic AI initiative across energy customer digital platforms. You will translate business intent into scalable, governed, production ready systems, and hold the architectural line across delivery teams as the primary technical contact for business leaders and platform partners.

Key Responsibilities

• Design and govern end to end agentic architecture for customer digital experiences spanning apps, billing, payments and energy service workflows


• Architect multi agent orchestration patterns, including orchestrator and subagent hierarchies, tool and function calling, stateful graph based workflows and agent memory


• Set MCP (Model Context Protocol) standards for governed tool and enterprise service exposure


• Define runtime guardrails, including spend controls, billing integrity and fraud detection hooks, human review checkpoints and audit trails


• Lead the integration of AI agents with energy and utilities systems, including customer and billing platforms, metering and usage data, tariffs and pricing, outage management and field service


• Set LLMOps standards covering prompt versioning, RAG pipeline governance, evaluation harnesses and observability across latency, token cost, drift and safety


• Act as the primary technical interface between business leaders, delivery teams and platform partners

Ideal Background

• 12 to 18 years in enterprise or platform architecture, including 3 to 4 years or more delivering AI, machine learning or GenAI systems in production


• Strong command of API led design, distributed systems, event driven architecture and real time data


• Production experience with LLM based agent systems, shipped and not just prototyped


• Hands on with agent frameworks such as LangGraph, LangChain, Semantic Kernel, CrewAI or AutoGen, with sound judgment on architectural patterns


• Working knowledge of ReAct and plan and execute patterns, multi agent handoffs, RAG pipeline design (chunking, hybrid retrieval, reranking), prompt engineering and MCP


• Clear view of agent failure modes, including hallucination, tool misuse, cost runaway and infinite loops, and how to architect against them


• LLMOps exposure, including evaluation frameworks, observability tooling such as LangSmith or Langfuse, and prompt and model lifecycle management


• Meaningful exposure to energy or utilities systems such as customer information and billing, metering and usage data, tariffs and pricing, demand programs, outage management or field service, with direct sector experience strongly preferred and adjacent regulated industry backgrounds considered


• Comfortable with Kafka or equivalent event streaming and the realities of enterprise data quality; semantic models or knowledge graphs as grounding layers are a plus


• Hands on enough to write reference implementations and lead code reviews, with Python proficiency expected


• Credible at executive level, able to set architectural boundaries, make trade off calls and defend them under pressure


• Experience leading across onshore and offshore delivery models

Package

The compensation package offered includes a base salary of up to $220,000 with a 30% bonus. This can be negotiable depending on experience.