Technical Specialist/ Senior AI Engineer – Generative & Conversational AI

Job Description

Key Responsibilities

• Design and build Generative AI solutions using LLMs, RAG, semantic retrieval, contextual reasoning, tool/function calling, and AI orchestration.
• Build ingestion, embedding, retrieval, reranking, and context-construction pipelines for enterprise knowledge.
• Develop real-time conversational AI using Speech-to-Text, Text-to-Speech, streaming audio, and session management.
• Implement conversation context, structured memory, grounding against approved knowledge sources with source traceability, knowledge boundaries, intelligent routing, confidence handling, and fallback mechanisms.
• Build AI evaluation and automated regression testing for accuracy, relevance,
  groundedness, hallucination, consistency, and safety.
• Implement AI guardrails and security controls for prompt injection, inappropriate content, PII/data leakage, and out-of-scope requests.
• Optimise AI systems for low latency, high concurrency, scalability, resilience, and cost efficiency.
• Integrate AI services with enterprise platforms using APIs, queues, asynchronous processing, streaming, and event-driven architectures.
• Implement AI observability and troubleshoot production issues across models, retrieval, orchestration, latency, and quality.
• Contribute to architecture, technical design, documentation, code reviews, engineering standards, production readiness, and AI testing strategies, while continuously improving prompts, retrieval strategies, model configuration, and AI workflows.

Desired Skills

• LLMs & LLM APIs
• Retrieval-Augmented Generation (RAG) - embeddings, chunking, semantic/vector search, hybrid search, retrieval, reranking, and context construction
• Strong Python development
• Prompt engineering and structured LLM outputs
• Tool/function calling and AI workflow orchestration
• Multi-turn conversation, session context, and structured memory
• Speech / Conversational AI - STT, TTS, streaming audio, VAD, and streaming AI responses
• Designing low-latency, high-concurrency AI systems
• AI evaluation and automated regression testing
• AI guardrails and security - hallucination control, prompt injection, PII/data leakage, and access controls
• Backend integration using REST APIs, asynchronous processing, queues, streaming, and event-driven architectures
• Production AI engineering covering scalability, resilience, observability, caching, and cost optimisation
• Ability to investigate ambiguous AI behaviour, translate business requirements into measurable AI behaviours and acceptance criteria, and explain AI design decisions and trade-offs clearly
• Strong software engineering practices including architecture, automated testing, debugging, version control, code reviews, and maintainable development
• Multilingual LLM, STT, or TTS solutions
• Multimodal AI using text, documents, images, and audio
• Experience with multiple model providers and model routing / provider abstraction
• Human-in-the-loop AI, confidence-based escalation, moderation, or approval workflows
• Cloud-native AI services on Azure, AWS, or Google Cloud
• Enterprise SaaS concepts including multi-tenancy, RBAC, tenant isolation, auditability, and regulated data handling

Added Advantage

• Experience with LLM benchmarking, evaluation datasets, or AI evaluation/observability platforms
• Knowledge graphs, ontology, taxonomy, or semantic enrichment
• Advanced information-retrieval techniques
• Experience with specific vector/search platforms such as Azure AI Search,
• Elasticsearch/OpenSearch,
• Pinecone, Weaviate, Qdrant, or pgvector

Experience

• Typically 5+ years of software engineering experience
• At least 2+ years of applied AI/ML or Generative AI engineering experience

Qualifications

• Bachelor’s degree in Computer Science, Software Engineering, Artificial Intelligence, Data Science, or a related discipline, or equivalent professional experience.