AI Engineer (LLM)

Job Context:

We are seeking a senior, hands-on AI Engineer to design, build, and productionize LLM-powered applications and agentic automation workflows across business-critical processes. This role is focused on delivering production-ready capabilities integrated into enterprise systems, with measurable outcomes such as productivity gains, cycle time reduction, ticket reduction, cost reduction, and, where applicable, revenue impact. The AI Engineer will work closely with architecture, engineering, and business stakeholders to ensure solutions align with internal standards, security requirements, and technology guidelines.

Job Responsibilities:

Design and develop LLM-powered applications for enterprise use cases using OpenAI and/or Azure OpenAI capabilities.
Implement agentic workflow patterns including tool/function calling, multi-step task execution, routing, retries, and human-in-the-loop controls where appropriate.
Build and maintain backend services and APIs supporting AI-driven automation and integration with internal platforms.
Design and implement Retrieval-Augmented Generation (RAG) solutions, including document ingestion, chunking strategies, embeddings, retrieval/search, ranking or re- ranking, and response grounding.
Integrate AI-enabled workflows with internal systems through APIs and services, and support UI-driven automation patterns in cases where APIs are not available.
Define and implement testing and evaluation approaches for AI solutions, including functional testing, regression testing, automated evaluation, and failure mode validation.
Implement observability and monitoring for AI services (quality, latency, error rates, and cost), and support troubleshooting in production environments.
Maintain prompt and configuration assets using enterprise-grade governance practices (versioning, change control, review, and promotion across environments), aligned with internal engineering standards.
Collaborate with Data Engineers, Software Engineers, Deployment Engineers, and process stakeholders to deliver end-to-end outcomes.

Educational Requirements:

Bachelor’s or Master’s in Computer Science, Software Engineering, AI/ML, Data Science, or related field. Strong programming foundation (Python) and AI/ML expertise are critical.

Required Skills and Experience:

Strong software engineering foundation with a focus on maintainability, robustness, and production reliability.
Strong Python development experience (mandatory).
Proven experience delivering LLM applications into production (beyond prototypes and demos).
Experience with OpenAI APIs and/or Azure OpenAI Service, including practical prompt engineering and structured output patterns.
Practical understanding of RAG, embeddings, vector search, and grounding strategies.
Experience integrating AI solutions into enterprise ecosystems via APIs and service interfaces. Experience working with enterprise platforms such as SAP and ServiceNow is a strong plus.
Strong debugging and troubleshooting capability in production environments.
Ability to work independently with high ownership and accountability for delivery outcomes.

Nice to have:

Experience implementing structured evaluation approaches such as LLM-as-a-judge, prompt A/B testing, and RAG performance scoring.
Experience deploying enterprise AI services with strong security controls, including secure network patterns (for example VNet integration / Private Link-style connectivity, restricted egress, and enterprise access controls where applicable).
Experience building agent orchestration using frameworks such as LangChain (or equivalent).
Experience with vector search platforms such as Azure AI Search, pgvector, Pinecone, Weaviate, or equivalent.
Familiarity with LLM observability and monitoring practices, including telemetry, tracing, and prompt/version governance.
Experience optimizing LLM-heavy workloads (token budgets, caching, batching, model selection strategies, latency and cost tuning).

Technology Stack (Indicative):
(Final stack and tooling will follow internal standards and may vary by domain.)

OpenAI / Azure OpenAI
Python
API development and enterprise integration
Retrieval and search technologies supporting RAG patterns
Cloud services (Azure-first where applicable)
Containerization and orchestration (Docker, Kubernetes)
CI/CD pipelines and release management
GitOps deployment patterns (where applicable)

Cross-Cutting Expectations:

Strong delivery mindset with a focus on measurable outcomes.
High ownership and accountability for quality, reliability, and timelines.
Ability to collaborate effectively across engineering, architecture, and business stakeholders.
Structured execution and clear communication suitable for enterprise delivery environments.

Success Measures (Examples):

AI workflows delivered on agreed timelines with stable production performance.
Demonstrable business outcomes such as ticket reduction, cycle-time reduction, and/or productivity gains.
AI services meet agreed operational expectations (monitoring, incident readiness, measurable reliability).
Consistent AI output quality validated through testing and evaluation practices.
Demonstrated ability to optimize token usage, model selection, and latency to achieve a strong cost-to-value ratio while maintaining the required output quality.

Workplace: