Generative AI Engineer
Gen AI engineer – Energy Trading
Our Energy Trading client is looking to build out an AI team to work on a number of projects across their business. They are seeking an engineer who can take an idea for an intelligent agent and turn it into a reliable, production-ready system.
What You'll Be Working On
- Designing and refining autonomous AI agents using modern orchestration frameworks (e.g., LangGraph, Semantic Kernel) and a mix of cloud-hosted and open-source language models.
- Developing complete agent workflows, from event triggers to model endpoints to user-facing integrations. Expect to work with systems like n8n, Ray Serve, vector stores (pgvector, cloud search), and messaging surfaces such as Teams or similar platforms.
- Building and operating cloud infrastructure using container orchestration and infrastructure-as-code tools (e.g., Kubernetes, Terraform/Bicep, CI/CD pipelines).
- Implementing secure-by-default systems, including identity management, secrets handling, and automated access controls.
- Monitoring and optimizing performance, using observability tooling to track cost, latency, throughput, and agent quality.
- Collaborating directly with domain specialists to iterate rapidly—turning sketches into working prototypes in weeks, not months.
What We're Looking For
- 4–6 years of software engineering experience, including at least two years deploying workloads on a major cloud provider.
- Strong Python skills (async, typing, production code practices) alongside practical TypeScript experience for bot or workflow integrations.
- Hands-on experience with LLM or conversational-AI systems, including model APIs, RAG patterns, or agent frameworks.
- Solid Kubernetes and Docker skills, with at least one real production service shipped in containers.
- Good command of SQL and data workflows, ideally with relational stores and event-streaming systems.
- A track record of owning solutions end-to-end, especially those used by internal teams or external customers.