Opportunity Description AI Engineer
Our end client a technology-driven organization focused on data engineering, AI, cloud solutions, and digital transformation — delivers innovative technology solutions that help businesses modernize their data infrastructure, leverage artificial intelligence, and build scalable digital platforms. The organization works on advanced technology initiatives across enterprise and data-intensive environments.
They are looking for an experienced AI Engineer to design, develop, and deploy intelligent AI/ML solutions, working with modern AI technologies to solve complex business challenges. This is a high-impact opportunity for professionals who enjoy building production-ready AI systems, working with cross-functional teams, and contributing to next-generation AI-driven solutions.
Role & responsibilities
- Build and own sub-agents: typed input/output schemas, versioned prompts, a
constrained tool set, and a published success metric for each
- Design the orchestration layer planning, replanning, tool-failure recovery, and
handoff between supervisor and sub-agents
- Build the eval harness that decides when an agent is safe to promote from shadow
to assisted to autonomous
- Work the two-tier model setup: a heavy model for judgment and classification, a
lighter self-hosted tier for high-volume extraction and formatting
- Make agent behavior observable and debuggable traces, cost per agent, failure
attribution
Preferred candidate profile
- You've shipped LLM systems into production, not just demos. You can talk about
what broke and what you changed.
- Comfortable with agent orchestration in some form — LangGraph, custom runtimes, workflow engines, or your own. We care more about the reasoning than the library.
- Strong Python. Go or TypeScript useful.
- You've built evals, or you've felt the pain of not having them.
- Solid on structured output, schema validation, and getting reliable behavior out of unreliable models.
Nice to have
- Durable execution experience — Temporal, Cadence, Step Functions, or similar
- Self-hosted inference: vLLM, TGI, quantisation, GPU scheduling
- Retrieval systems at scale, and knowing when not to use them
- Document understanding: OCR, layout parsing, extraction from messy PDFs
- Anything regulated — audit trails, approval workflows, compliance reporting