AI Engineer (Agentic Systems, Full-Stack)
TLDR
Design and develop intelligent, automated workflows using large language models and building scalable backend services with a focus on AI-driven applications.
AI Engineer (Agentic Systems, Full-Stack)
Overview:
We are seeking a skilled AI engineer to join our team. In this role, you will be responsible for designing and developing agentic systems that leverage large language models and data to create intelligent, automated workflows. You will work across the full stack, integrating data sources, building backend services, and enabling user-facing applications powered by AI.
You will use APIs, databases, and other data sources to support AI-driven applications, and collaborate with analytics and engineering teams to ensure solutions are scalable, accurate, and aligned with business needs.
Responsibilities:
Design and develop agentic systems, including multi-agent workflows and orchestration pipelines
Build and integrate LLM-powered applications using APIs and modern AI frameworks
Develop backend services (APIs, microservices) to support AI-driven workflows
Work with data from various sources (APIs, databases, files) to support AI use cases
Transform and prepare data for use in AI models and applications
Collaborate with analytics and visualization engineers to ensure outputs meet business requirements
Assist in building and maintaining lightweight data pipelines as needed
Evaluate and improve prompting strategies, embeddings, and retrieval techniques
Monitor and optimize system performance, including latency, cost, and accuracy
Stay up-to-date with new AI engineering techniques and technologies and apply them as needed
Requirements:
Bachelor's degree in a relevant field such as Computer Science, Data Science, or a related field
1–2 years of professional experience building or supporting software or AI-driven systems in a work environment (internships and co-ops included)
Hands-on experience working with LLM-based applications or agentic workflows in a professional or production setting
Strong programming skills, including experience with: Python (preferred), Java (optional), Scala (optional)
Experience working with APIs and backend development frameworks (e.g., Flask, FastAPI) in a job setting
Familiarity with LLM frameworks or platforms (e.g., LangChain, LangGraph, OpenAI, Gemini)
Basic SQL skills and experience working with structured and unstructured data
Experience contributing to applications or pipelines deployed in cloud environments such as GCP, AWS, or Azure
Understanding of data pipelines, APIs, and system integrations
Excellent communication and collaboration skills in a team-based environment
Ability to work independently and manage multiple tasks and priorities
Syntasa UK builds advanced data engineering solutions that focus on designing scalable data pipelines and optimizing cloud workloads. We cater to organizations looking to enhance their data capabilities and performance, leveraging expertise in high-performance cloud architecture to deliver robust solutions.