General Description:

We are looking for a Forward Deployed Engineer who uses Generative AI as a foundation of software engineering. This role applies AI across the full Product Development Lifecycle, from requirements and design to deployment and operations. You will design and build AI Agents, apply advanced prompting techniques, and implement architectures like RAG, ReAct, and Chain of Thought. You will also leverage short and long-term memory, MCP, A2A, ACP, and Agentic AI patterns. The ideal candidate uses AI IDEs every day and sees AI not as a tool but as the core of modern engineering.

Responsibilities:

• Translate product and engineering challenges into AI-driven solutions that enhance speed, quality, and outcomes

• Build and deploy AI Agents with advanced reasoning, integrating memory, MCP, custom MCP servers, and A2A

• Apply prompt engineering, context engineering, AI steering, RAG, Chain of Thought, ReAct, and other modern AI frameworks to real-world use cases

• Partner with product and engineering teams to embed AI, LLMOps, and observability into requirements, coding, testing, monitoring, and operations

• Prototype, test, optimise, fine-tune, and scale AI solutions, balancing experimentation with production readiness and inference deployment

• Design, run, and automate evals to test LLM outputs for quality, reliability, and safety

• Implement security guardrails and robust data integration across agentic workflows to mitigate vulnerabilities

• Support pre-sales and client discussions by demonstrating applied AI use cases and outcomes

• Stay ahead of research and practice in GenAI and bring them into daily engineering practice

• Communicate findings and trade-offs clearly to both technical teams and executives

Required qualifications:

• Bachelor's Degree in Computer Science, Engineering, Applied Math, or related fields

• Strong programming background in Python (or similar) with experience in GenAI frameworks and APIs

• Daily use of Generative AI IDEs or environments

• Proven experience in Prompt Engineering, Context Engineering, AI Steering, RAG, MCP (Model Context Protocol) and building agent workflows

• Solid experience with LLMOps, structured Evals, and LLM observability/tracing tools

• Proven knowledge of GenAI Security practices (guardrails, prompt injection mitigation) and secure data integration

• Solid understanding of A2A (Agent to Agent) and ACP (Agent Coordination Protocol)

• Experience in deploying AI-powered solutions across the product development lifecycle, from design to monitoring

• Understanding of how to integrate short and long-term memory in agents

• Strong communication skills in English, both technical and business-oriented

• Exposure to cloud native environments

• Ability to work independently and collaboratively in fast-paced environments

Desired qualifications:

• Knowledge of reasoning strategies (Chain of Thought, ReAct)

• Experience with Agentic AI frameworks, autonomous agents and Multi-Agent Orchestration frameworks (e.g., LangGraph, CrewAI)

• Hands-on experience with LLM optimisation, Fine-Tuning techniques, and production inference deployment

• Experience developing custom MCP (Model Context Protocol) servers to connect agents with external tools and data

• Experience designing and applying evals to validate LLM outputs

• Experience with Knowledge Graphs, or hybrid RAG approaches

• Experience monitoring AI systems for performance, accuracy, and cost