Staff AI Engineer

Harnham; New York (NY); Remote; USD 160,000 - 185,000; Full time

Job summary

Harnham is seeking a senior AI engineering leader to design, develop, and deploy large-scale AI applications for enterprise clients. This role owns end-to-end solution architecture, guides technical direction, and delivers production-ready AI systems with a focus on scalability, security, reliability, and operational excellence.

The role spans generative AI, agent-based architectures, cloud-native platforms, and ML systems, collaborating with engineering teams and client stakeholders to drive

Qualifications

• 5+ years of software engineering delivering production AI / ML solutions.
• Experience building agentic AI systems, LLM orchestration, tool/calling, and RAG architectures.
• Proficiency with AWS services (Bedrock, SageMaker, Lambda, DynamoDB, S3).

Responsibilities

• Architect and implement advanced AI solutions, including agent-based systems and multi-agent environments.
• Design and optimise Retrieval-Augmented Generation platforms using embeddings, vector databases, search, and knowledge retrieval.
• Build cloud-based AI applications using managed services, serverless patterns, and APIs.
• Establish evaluation, monitoring, observability, and testing for production LLM apps.
• Develop backend services and APIs with modern cloud-native design patterns.
• Lead technical architecture discussions and mentor engineering teams.
• Drive engineering best practices, standards, and solution reviews.
• Improve system resilience with fault-tolerant architectures and monitoring.
• Collaborate with business stakeholders to deliver scalable AI solutions.

Skills

AWS cloud services

Python

Node.js

LLM orchestration

RAG architectures

Docker

Distributed systems

Architectural leadership

Education

Bachelor's degree in CS/Engineering

Tools

Amazon Bedrock

SageMaker

Lambda

DynamoDB

S3

Job description

Location: Remote (United States, Eastern or Central time zones preferred)

Travel: Approximately 10-20% travel for client meetings and team collaboration

Compensation: Base salary range of $160,000-$185,000

Overview

A technology consulting organisation is seeking a senior AI engineering leader to design, develop, and deploy large-scale AI applications for enterprise clients. This role is suited to an experienced engineer who enjoys owning end-to-end solution architecture, guiding technical direction, and delivering production-ready AI systems with a focus on scalability, security, reliability, and operational excellence. The successful candidate will work across generative AI, agent-based architectures, cloud-native platforms, and machine learning systems while collaborating with engineering teams and client stakeholders.

Key Responsibilities

• Architect and implement advanced AI solutions, including agent-based systems, reasoning workflows, tool integration, and multi-agent environments.
• Design and optimise Retrieval-Augmented Generation (RAG) platforms leveraging embeddings, vector databases, search, ranking, and knowledge retrieval strategies.
• Build and integrate cloud-based AI applications using managed services, serverless technologies, event-driven architectures, APIs, and data platforms.
• Establish evaluation, monitoring, observability, and testing frameworks for production LLM applications.
• Develop backend services and APIs using modern programming languages and cloud-native design patterns.
• Lead technical architecture discussions and provide guidance to engineering teams across AI initiatives.
• Mentor developers and contribute to engineering best practices, standards, and solution design reviews.
• Improve system resilience through fault-tolerant architectures, monitoring, fallback strategies, and operational excellence practices.
• Partner with business and technical stakeholders to deliver scalable AI solutions aligned with client objectives.

Required Qualifications

• 5+ years of software engineering experience with demonstrated success delivering production AI, machine learning, or generative AI solutions.
• Strong experience building agentic AI systems, LLM orchestration frameworks, tool/function calling, and RAG architectures.
• Deep expertise with AWS services, including:
  • Amazon Bedrock
  • SageMaker
  • Lambda
  • DynamoDB
  • S3
  • Event-driven services and workflow orchestration technologies
• Proficiency in Python and Node.js, including API development and cloud-native application design.
• Experience implementing AI observability, evaluation methodologies, prompt engineering, and production monitoring practices.
• Hands-on experience with containerisation technologies such as Docker.
• Strong understanding of distributed systems, scalability, and modern software architecture principles.
• Bachelor's degree in Computer Science, Engineering, or a related technical field (or equivalent professional experience).

Preferred Qualifications

• Experience designing enterprise-scale AI platforms for multiple business stakeholders or client environments.
• Prior consulting, professional services, or client-facing delivery experience.
• Experience leading technical teams, mentoring engineers, and influencing architecture decisions.
• Familiarity with AI monitoring and evaluation platforms such as LangFuse, LangSmith, or similar tooling.