Job Description

1. Job Overview

We are looking for an experienced AI Engineer to design, develop, and deploy production-ready AI agents on an enterprise agent platform.

In this role, you will be responsible for building the core infrastructure that enables AI agents to operate reliably, securely, and efficiently in enterprise environments. You will also develop specialised AI agents to support various business use cases, including document extraction and reconciliation, regulatory change monitoring, and Business Intelligence (BI) queries.

This is a hands-on engineering role requiring strong software engineering fundamentals, practical experience with LLM applications and agentic workflows, and the ability to translate business requirements into scalable technical solutions.

You will work closely with cross-functional teams and business stakeholders to deliver AI-powered solutions while ensuring quality, security, observability, and production readiness.

2. Key ResponsibilitiesAgent Platform & Harness Engineering

Design and develop the harness layer for enterprise AI agents, including tool interfaces, context assembly, control loops, guardrails, human-in-the-loop checkpoints, evaluation suites, and fallback mechanisms.
Build specialised AI agents on the enterprise platform to support business unit use cases, such as document extraction and reconciliation, regulatory change monitoring, and BI queries.
Implement agent control loops using open-source frameworks such as LangGraph or equivalent technologies.
Run comprehensive harness testing cycles on the enterprise agent platform and collaborate with platform teams to identify issues and implement improvements.

AI Security & Reliability

Design and implement platform-level guardrails, including input/output validation, PII handling, policy enforcement, and prompt injection defence.
Define fallback strategies for low-confidence responses, tool failures, and execution timeouts.
Establish appropriate human review checkpoints to ensure accuracy, reliability, and compliance in business-critical workflows.
Ensure AI agents operate within defined security, governance, and business policy requirements.

System Integration & Development

Integrate AI agents with enterprise data sources and business systems through platform connectors and custom tools.
Implement tool/function calling, structured outputs, retrieval mechanisms, and context management under token and cost constraints.
Work with structured and unstructured data, including SQL databases, PDFs, emails, and scanned documents.
Configure and customise AI agents based on individual business unit requirements and domain-specific rules during fit-gap delivery.

Monitoring & Evaluation

Design and implement evaluation frameworks for AI agents, including offline evaluation datasets, regression test suites in CI, and LLM-as-a-Judge mechanisms calibrated against human reviews.
Instrument AI agents with tracing, logging, cost monitoring, and latency tracking to identify and diagnose production issues.
Establish observability practices using tools such as OpenTelemetry, Google Cloud Trace, Langfuse, or equivalent solutions.
Continuously monitor agent performance and improve reliability, response quality, and operational efficiency.

Technical Leadership & Collaboration

Review technical designs and code developed by other AI engineers, ensuring consistency with engineering standards and best practices.
Collaborate with business stakeholders and cross-functional teams to understand requirements and translate user stories into technical implementations.
Work within an Agile Scrum environment, delivering solutions against defined acceptance criteria.
Support presales activities by providing effort estimations, component diagrams, and technical sections of client proposals.

3. RequirementsEducation & Professional Experience

Bachelor's degree in Computer Science, Software Engineering, Information Technology, or a related field.
At least 5 years of professional software engineering experience.
At least 2 years of hands-on experience building and deploying production-grade LLM applications or AI agents.
Proven experience implementing evaluation and monitoring mechanisms for production AI systems.

Technical Skills

Programming & AI Development

Strong proficiency in Python, including production-quality coding, testing, and packaging.
Hands-on experience developing LLM applications and agentic workflows.
Solid understanding of tool/function calling, structured output generation, retrieval mechanisms, and context window management.
Ability to optimise token consumption, execution costs, and agent performance.

Enterprise AI Platforms & Frameworks

Practical experience with at least one enterprise agent platform, such as:
Dataiku
Gemini Enterprise
Vertex AI Agent Builder
Agent Development Kit (ADK)
Agent Engine
Equivalent enterprise AI platforms on other cloud providers.
Ability to implement agent control loops using open-source frameworks such as LangGraph or similar technologies.

AI Evaluation & Guardrails

Experience designing evaluation frameworks, including offline datasets, regression testing in CI, and LLM-as-a-Judge.
Understanding of evaluation calibration against human review.
Hands-on experience implementing AI guardrails, including:
Input and output schema validation.
Policy and rule-based checks.
Prompt injection defence.
Personally Identifiable Information (PII) detection and handling.

Cloud, DevOps & Observability

Experience with Google Cloud Platform (GCP), particularly Vertex AI, Cloud Run, and IAM, or equivalent cloud services.
Experience with containers and CI/CD pipelines, preferably GitLab CI/CD.
Familiarity with agent observability and monitoring tools such as OpenTelemetry, Google Cloud Trace, Langfuse, or equivalent.

Data & Document Processing

Strong SQL skills and experience working with enterprise data sources.
Experience with document parsing and extraction from PDFs, emails, scanned forms, and other unstructured data formats.

Soft Skills

Fluent English communication skills, with the ability to work effectively in professional, cross-functional, and client-facing environments.
Strong analytical and problem-solving abilities.
Ability to work independently, take ownership of technical deliverables, and collaborate with distributed teams.
Comfortable working in an Agile Scrum environment, following user stories and defined acceptance criteria.

4. Preferred Qualifications

Experience with agent-to-agent interoperability, including A2A (Agent-to-Agent) protocol and MCP (Model Context Protocol) servers.
Experience working with data platforms such as BigQuery, AWS Glue, Amazon Athena, or Power BI to support AI agents, analytics, and dashboards.
Previous experience mentoring engineers, reviewing technical work, or leading a small engineering team.
Experience delivering enterprise AI solutions in regulated industries or complex business environments.