Technical Specialist - AI Engineering

Job Description

About the Role

We are looking for an experienced AI Engineer to design and build production-grade Generative AI capabilities for enterprise applications. The role will focus on
developing reliable AI systems that combine Large Language Models, retrievalaugmented generation, contextual reasoning, multimodal interactions, and intelligentnworkflow orchestration.

The successful candidate should be comfortable working across models, retrieval,
orchestration, data, application integration, evaluation, and production engineering, and should be able to make pragmatic engineering decisions where AI behavior is probabilistic rather than deterministic. You should enjoy solving complex problems, experimenting systematically, measuring results, and turning emerging AI capabilities into dependable software products.

Key Responsibilities

• Design and implement Generative AI capabilities using LLMs, RAG, semantic retrieval, contextual reasoning, and agent/workflow orchestration.
• Build AI pipelines that ingest, process, index, retrieve, and reason over structured and unstructured enterprise content.
• Develop mechanisms for grounding AI responses in approved knowledge sources while maintaining source traceability and contextual relevance.
• Design conversation and session-context management for stateful AI experiences, including short-term context and persistent structured memory where appropriate.
• Implement intelligent routing and decision logic for handling different query types, confidence levels,
• knowledge boundaries, and fallback scenarios.
• Develop AI evaluation mechanisms covering response accuracy, relevance, groundedness, hallucination risk, consistency, and quality.
• Implement guardrails and safety controls for inappropriate content, sensitive information, prompt manipulation, and out-of-scope requests.
• Optimize AI workflows for low-latency, high-throughput production environments while balancing response quality, model cost, and scalability.
• Integrate AI services with application platforms through APIs, event-driven interfaces, and other backend integration patterns.
• Design provider-independent AI components that allow models or AI services to be changed with minimal impact to the wider application.
• Implement telemetry for model usage, token consumption, response latency, failures, confidence indicators, and AI operational health.
• Investigate production AI issues, analyse model behaviour, and continuously improve prompts, retrieval strategies, orchestration logic, and evaluation criteria.
• Contribute to architecture reviews, technical design, engineering standards, documentation, code reviews, and production-readiness activities.
• Collaborate with QA and engineering teams to define automated test strategies for probabilistic AI behaviour in addition to conventional software testing.

Required Skills and Experience

• Bachelor’s degree in Computer Science, Artificial Intelligence, Software Engineering, Data Science, or a related discipline, or equivalent professional experience.
• Strong professional experience developing AI/ML or Generative AI solutions in production environments.
• Hands-on experience working with commercial or open-source Large Language Models and their APIs.
• Strong understanding of Retrieval-Augmented Generation, including chunking strategies, embeddings, semantic search, retrieval, reranking, and context construction.
• Experience developing LLM-based applications using Python and modern AI application frameworks or equivalent custom implementations.
• Strong understanding of prompt engineering, structured outputs, tool/function calling, conversation management, and LLM orchestration.
• Experience integrating AI services with backend systems using REST APIs, asynchronous processing, queues, or event-driven architectures.
• Strong software engineering fundamentals, including API design, automated testing, version control, debugging, code quality, and maintainable architecture.
• Practical experience evaluating AI output using measurable quality criteria rather than relying solely on manual prompt testing.
• Understanding of AI security and responsible-AI concerns, including prompt injection, data leakage, hallucination control, PII handling, and model access controls.
• Experience designing AI applications with production considerations such as scalability, resilience, observability, latency, and cost optimization.
• Ability to investigate ambiguous AI behavior systematically and translate business requirements into technically measurable AI behaviors.
• Strong written and verbal communication skills with the ability to explain AI design decisions and trade-offs to both technical and non-technical stakeholders.

Preferred Skills

• Experience with speech AI, including Speech-to-Text, Text-to-Speech, streaming audio, voice activity detection, or real-time conversational AI.
• Exposure to multimodal AI involving combinations of text, images, documents, audio, or other content types.
• Experience with vector databases or search technologies such as Azure AI Search,Elasticsearch/OpenSearch, Pinecone, Weaviate, Qdrant, pgvector, or equivalent platforms.
• Familiarity with LLM evaluation and observability platforms, model-quality benchmarking, automated evaluation datasets, or regression testing for Generative AI.
• Experience working with multiple LLM/model providers and implementing abstraction or routing strategies across providers.
• Knowledge of knowledge-graph, ontology, taxonomy, semantic enrichment, or advanced informationretrieval techniques.
• Experience with high-concurrency or near-real-time systems where AI response latency is a key design constraint.
• Familiarity with cloud-native AI services and deployment patterns across Azure, AWS, or Google Cloud Platform.
• Exposure to Kubernetes, containers, CI/CD, infrastructure-as-code, and production AI platform operations.
• Experience developing enterprise SaaS solutions involving multi-tenancy, role-based access, data isolation, auditability, or regulated data.
• Familiarity with human-in-the-loop AI workflows, confidence-based escalation, AI moderation, or review/approval mechanisms.

Qualifications

• Bachelor’s degree in computer science, Software Engineering, Artificial Intelligence, Data Science, or related discipline, or equivalent professional experience.
• Typically, 8+ years of software engineering with 2+ years of applied AI/ML experience, including meaningful hands-on experience delivering Generative AI solutions.