Senior AI Engineer

Job Description

Key Responsibilities:

Engineering 

• Design, develop, and deliver complex, scalable application solutions with a focus on performance, security, and maintainability.
• Own end-to-end solution architecture for large features or systems, including microservices, APIs, and event-driven workflows.
• Lead the design and implementation of reusable components, frameworks, and engineering patterns.
• Ensure high code quality through rigorous testing strategies, code reviews, and adherence to best practices.
• Define and document architecture decisions, technical designs, and system dependencies.
• Design and implement secure AI solutions using Azure security best practices.
• Secure Azure OpenAI, AI Foundry, AI Search, and AI workloads through identity, access control, and network security.
• Define and enforce Responsible AI, security, privacy, and governance standards across AI applications. 
• Ensure data protection, auditability, compliance, and regulatory adherence for AI-enabled solutions. 
• Implement AI guardrails, content filtering, model monitoring, and risk controls for GenAI applications. 
• Conduct security reviews, threat modelling, and vulnerability assessments for AI services and integrations.
• Collaborate with Security Operations, Risk, Compliance, and Governance teams to ensure enterprise-wide AI security standards. 
• Monitor and respond to security risks associated with LLMs, AI agents, APIs, and enterprise integrations.
• Establish secure patterns for RAG, vector databases, embeddings, and enterprise knowledge access.

Advanced Development & Delivery

• Independently deliver complex workstreams and mission-critical features with minimal oversight.
• Provide accurate estimations, identify risks, and proactively manage trade-offs and dependencies.
• Lead root cause analysis and resolution of complex production issues and system defects.
• Drive CI/CD, observability, and reliability improvements across systems.

GenAI & Agentic Systems

• Architect and implement AI-assisted and agentic workflows that decompose complex tasks into orchestrated steps.
• Design and build advanced AI agents capable of reasoning, decision-making, and tool usage.
• Define when to apply human-in-the-loop vs autonomous agentic patterns.
• Lead the integration of LLMs with enterprise systems, APIs, and knowledge bases.
• Establish robust grounding strategies (RAG, embeddings, vector stores) to improve accuracy and reduce hallucinations.
• Continuously evaluate and improve model and agent performance using feedback loops and telemetry.

Governance & Standards

• Define and enforce engineering and AI governance frameworks, including ethical AI practices and compliance standards.
• Establish best practices for prompt engineering, agent design, and reusable AI components.
• Ensure data quality, security, and auditability across AI and application systems.
• Contribute to enterprise-wide standards for GenAI adoption and responsible AI usage.

Collaboration 

• Collaborate closely with product, architecture, and business stakeholders to align technical solutions with business goals.
• Influence technical roadmaps and contribute to long-term platform and capability strategy.
• Support change management and production deployments across environments.

Essential Skills & Experience

• 5+ years of experience in software engineering, with strong expertise in Python and React.js.
• 5+ years of experience designing and building RESTful APIs, microservices, and distributed systems.
• Proven experience in Generative AI, including LLM orchestration, LangChain (or similar frameworks), and prompt engineering.
• Strong understanding of system design, scalability, and performance optimization.
• Experience designing event-driven and asynchronous systems.
• Hands-on experience integrating AI systems with enterprise platforms and APIs.