AI Forward Deployed Engineer (FDE)

Ktek Talent Solutions; United States; Remote; USD 150,000 - 190,000; Full time

Job summary

Ktek Talent Solutions is seeking an experienced AI Engineer to design and deploy AI-powered applications and multi-agent workflows for enterprise clients. You will translate business problems into technical architectures, build scalable data pipelines, and ensure secure, reliable operations across cloud platforms.

Ideal candidates will have hands-on Python/TypeScript experience, strong knowledge of LLMs, prompt engineering, and experience with LangGraph/LangChain.

Qualifications

• Strong programming experience in Python, TypeScript or JavaScript with production-grade apps.
• Practical experience building and deploying LLM-powered apps, AI agents or agentic workflows.
• Deep understanding of LLM concepts, prompt engineering, tool calling, memory and context management.

Responsibilities

• Engage directly with clients to understand business requirements, workflows, and technical challenges.
• Translate ambiguous business problems into technical specifications, solution architectures, prototypes, and production-ready AI applications.
• Design, develop, and deploy AI-powered applications, intelligent agents, APIs, data pipelines, and full-stack solutions.
• Build and manage agentic workflows involving planning, tool selection, execution, observation, error recovery, and termination.
• Implement AI system components such as context management, memory, permissions, runtime controls, and observability.
• Develop workflow orchestration using graphs, state machines, and multi-step execution patterns.
• Integrate LLM-based solutions with enterprise applications, databases, APIs, cloud platforms, and third-party services.
• Build evaluation frameworks to measure AI accuracy, reliability, task completion, latency, and operational cost.
• Troubleshoot AI-related issues, including hallucinations, context loss, unreliable tool calls, infinite loops, and prompt injection.
• Collaborate with product, engineering, data, security, and client teams throughout the solution lifecycle, from discovery to production.
• Monitor, optimize, and maintain AI applications for scalability, performance, reliability, and security.
• Communicate technical designs, implementation risks, limitations, and trade-offs to technical and non-technical stakeholders.

Skills

Python

TypeScript

JavaScript

LLM concepts

Prompt engineering

Tool calling

Memory management

Agent orchestration

REST APIs

Cloud infrastructure

Tools

LangGraph

LangChain

REST APIs

Databases

Job description

Role & responsibilities

• Engage directly with clients to understand business requirements, workflows, and technical challenges.
• Translate ambiguous business problems into technical specifications, solution architectures, prototypes, and production-ready AI applications.
• Design, develop, and deploy AI-powered applications, intelligent agents, APIs, data pipelines, and full-stack solutions.
• Build and manage agentic workflows involving planning, tool selection, execution, observation, error recovery, and termination.
• Implement AI system components such as context management, memory, permissions, runtime controls, and observability.
• Develop workflow orchestration using graphs, state machines, and multi-step execution patterns.
• Integrate LLM-based solutions with enterprise applications, databases, APIs, cloud platforms, and third-party services.
• Build evaluation frameworks to measure AI accuracy, reliability, task completion, latency, and operational cost.
• Troubleshoot AI-related issues, including hallucinations, context loss, unreliable tool calls, infinite loops, and prompt injection.
• Collaborate with product, engineering, data, security, and client teams throughout the solution lifecycle, from discovery to production.
• Monitor, optimize, and maintain AI applications for scalability, performance, reliability, and security.
• Communicate technical designs, implementation risks, limitations, and trade-offs to technical and non-technical stakeholders.

Preferred candidate profile

• 7+ years of professional experience in software engineering, AI engineering, application development, or related technical roles.
• Strong hands-on programming experience in Python, TypeScript, or JavaScript, with a proven track record of delivering production-grade applications.
• Practical experience building and deploying LLM-powered applications, AI agents, or agentic workflows.
• Strong understanding of LLM concepts, prompt engineering, tool calling, context management, structured outputs, and memory.
• Experience with agent orchestration frameworks such as LangGraph, LangChain, or equivalent custom orchestration solutions.
• Hands-on experience with REST APIs, databases, cloud infrastructure, enterprise integrations, and modern software development practices.
• Familiarity with RAG architectures, embeddings, vector databases, AI evaluation, and production monitoring.
• Understanding of AI security, access control, data protection, and reliable agent execution.
• Experience taking solutions from business discovery and rapid prototyping through validation, deployment, and production support.
• Strong client-facing communication, problem-solving, debugging, and stakeholder management skills.
• Ability to work independently in a fast-paced, remote, customer-facing engineering environment.
• Flexibility to work in CST business hours.

Preferred: Experience in consulting, solutions engineering, professional services, enterprise AI implementations, multi-agent systems, and cloud-native deployments using AWS, Azure, or GCP.