We are seeking a Lead Generative AI Engineer with deep expertise in agent-based system development to design, implement, and scale multi-agent workflows for real-world production environments. The ideal candidate is a hands-on architect and builder—fluent in Python, AI orchestration frameworks, vector databases, and autonomous agent design—who thrives at the intersection of cutting-edge research and practical deployment.

REQUIRED QUALIFICATIONS

• Strong Python expertise (OOP, production-level code).
• Hands-on experience with LLM prompt engineering across leading models (GPT, Claude, Gemini, LLaMA, etc.).
• Deep understanding of agent-based systems: memory, planning, tool use, autonomous task execution, evaluation frameworks.
• Expertise with multi-agent orchestration frameworks (LangGraph strongly preferred; Autogen, CrewAI also valuable).
• Experience with vector databases (Azure AI Search, Pinecone, FAISS, Chroma) for embeddings and semantic retrieval.
• Knowledge of ETL pipelines and data transformation in batch and streaming architectures.
• Hands-on experience with CosmosDB or other NoSQL stores, schema design, and scaling strategies.
• Strong knowledge of Git/GitHub workflows (branching, PRs, CI/CD).
• Track record of staying at the forefront of GenAI research and applied tools.

PREFERRED QUALIFICATIONS

• Cloud deployment experience with Azure (preferred), AWS, or GCP.
• Familiarity with LLM fine-tuning, embeddings generation, and tool/plugin calling.
• Knowledge of observability and evaluation frameworks (human-in-the-loop, automated feedback loops, telemetry).
• Contributions to open-source AI frameworks or relevant publications.

ABOUT US

We are a software house with 18 years of experience and a global portfolio of projects. We help businesses modernize, scale, and innovate through custom software solutions — always with a focus on flexibility and quality. Our team embraces unconventional ideas and new technologies, delivering solutions that drive real impact. If you value professionalism, creativity, and a strong engineering culture, you’ll feel at home here.
Job Type: Full-time
Pay: £45,000.00-£102,000.00 per year

Experience:

• Lead Engineer: 3 years (required)
• AI Engineer: 2 years (required)

Work Location: Remot

• Architect and implement autonomous and semi-autonomous AI agents using frameworks like LangGraph (preferred), Autogen, CrewAI, or Bedrock.
• Design and optimize prompt engineering strategies to ensure reliable, scalable agent performance across diverse use cases.
• Build end-to-end agent pipelines integrating vector databases (Azure AI Search, FAISS, Pinecone, Chroma) with batch/streaming ETL workflows.
• Leverage CosmosDB and NoSQL databases to efficiently manage unstructured and semi-structured datasets.
• Integrate agent systems into APIs, products, and enterprise workflows while ensuring security, scalability, and resilience.
• Conduct performance tuning, observability, and safety evaluations of agent workflows in production environments.
• Contribute to code reviews, CI/CD pipelines, and engineering best practices using Git/GitHub workflows.
• Continuously track and evaluate emerging GenAI models, frameworks, and protocols to guide architecture and implementation decisions.