Role overview

TribalScale is seeking a Forward Deployed Engineer to embed with client teams and build AI-enabled software solutions that address complex business challenges. This role bridges software engineering, artificial intelligence, product development, and client delivery, combining hands-on technical work with trusted advisory responsibilities.

Key responsibilities

Work directly with clients to understand their business objectives, technical environments, data sources, and operational constraints.
Design and develop AI-powered applications, agentic workflows, APIs, data pipelines, and full-stack products that solve real-world problems.
Build the infrastructure around AI models, including prompt engineering, tool integration, context management, permissions, runtime controls, observability systems, and human oversight mechanisms.
Create and refine agent loops that handle planning, tool selection, execution, observation, reflection, recovery, and termination logic.
Model complex workflows using graphs, state machines, and orchestration patterns that coordinate models, tools, data systems, and human approvals.
Develop evaluation frameworks that measure task completion, accuracy, reliability, safety, latency, cost, and user value.
Build rapid prototypes and proofs of concept, validate them with users and representative evaluations, then evolve successful solutions into secure, scalable products.
Integrate solutions with client systems, enterprise data sources, cloud platforms, and third-party services.
Implement safeguards, permission boundaries, approval workflows, and fallbacks for autonomous and semi-autonomous systems.
Instrument applications to enable inspection of execution traces, diagnosis of failures, and performance improvement.
Identify and address failure modes including hallucinations, looping, tool call brittleness, context loss, prompt injection, and unsafe actions.
Communicate technical decisions, risks, and trade-offs clearly to both technical and non-technical stakeholders.

Requirements

Professional experience building and deploying production-grade software, ideally including AI-powered or agentic systems.
Strong proficiency in Python, TypeScript, or another language commonly used for AI applications, platforms, and developer tooling.
Practical understanding of harness engineering and the infrastructure required to enable AI agents to operate reliably.
Experience building or working with agent loops, including planning, tool selection, execution, observation, reflection, recovery, and termination patterns.
Familiarity with graph-based orchestration, state machines, and multi-step workflows for coordinating agents, tools, data, and human approvals.
Experience designing evaluation systems for AI applications, including task-based benchmarks, regression suites, model-graded evaluations, and human review processes.

What makes this role worth considering

This role offers the opportunity to work at the intersection of emerging AI technology and real client impact, with direct visibility into how your work creates measurable business value. You will operate as both an engineer and strategic technical advisor, translating ambiguous business challenges into working solutions while collaborating across product, design, data, and security teams throughout the engagement lifecycle.