Generative AI Engineer

We are seeking a Generative AI Scientist to design and deliver agent‑based, AI‑enabled solutions integrated into complex enterprise environments. This is a hands‑on engineering role, focused on building production‑grade AI systems that move beyond experimentation into scalable, secure, and measurable outcomes for our clients.

You’ll work closely with UST’s engineering teams, AI specialists, and business stakeholders to translate high‑value use cases into robust solutions.

What You’ll Be Doing:

Build Agent‑Based AI Systems

• Design and develop multi‑agent orchestration workflows (supervisor / sub‑agent patterns)
• Implement multi‑step, asynchronous pipelines to solve complex enterprise problems
• Integrate AI workflows into client systems via secure, well‑designed APIs

Develop LLM‑Enabled Applications

• Deliver end‑to‑end LLM‑powered features in production environments
• Design effective prompting strategies and context management
• Implement structured outputs, validation, and safety guardrails, aligned to responsible AI principles

Design Retrieval \& Data Pipelines (RAG)

• Build and optimise retrieval‑augmented generation (RAG) pipelines

Work with:

• Vector search and similarity retrieval
• Search and indexing systems
• Embeddings and content storage
• Caching strategies for performance and scalability

Backend \& Platform Engineering

• Develop Python‑based backend services (APIs, integrations, orchestration layers)
• Apply strong engineering discipline across testing, observability, and error handling
• Contribute to reusable assets and patterns within UST’s AI ecosystem

Cloud‑Native Delivery (AWS)

• Deploy and operate scalable solutions on AWS
• Ensure best practices across:
• Security and IAM
• Reliability and performance
• CI/CD and environment management

What We’re Looking For:

• Strong experience in Python backend engineering
• Hands‑on delivery of Generative AI / LLM‑based applications

Experience with:

• Agent frameworks (e.g. LangChain, LlamaIndex, or similar)
• Retrieval‑based systems (RAG, vector databases, embeddings)
• APIs, microservices, and asynchronous workflows
• Experience deploying production systems in AWS environments

Nice to Have:

• Experience with multi‑agent architectures
• Exposure to productionising AI systems at scale
• Knowledge of data pipelines, search infrastructure, and platform engineering

#UST