building and optimizing Large Language Model (LLM) inferences and creating robust web services. This includes developing event-driven and request-response systems to run RAG (Retrieval-AugmentedGeneration) answer generation pipelines, essential for delivering sophisticated AI-driven solutions. Your role will require … an understanding of LLM frameworks such as Haystack, LlamaIndex, and LangChain, with a focus on Retrieval-AugmentedGeneration (RAG) and text/chat generators. Cloud computing with AWS (ECS, EKS, DynamoDB, Bedrock) Knowledge of git version control, branching, and code versioning. Passionate about code More ❯
natural language processing (NLP) tasks (summarisation, sentiment analysis, keyword extraction, categorisation). Develops and maintains retrieval-augmentedgeneration (RAG) systems, indexing, embedding, and reranking. Builds evaluation frameworks assessing AI output faithfulness, relevance, and truthfulness. Enhances solutions with a focus on efficient compute usage for … with AutoML libraries (e.g., AutoKeras). Solid experience with natural language processing ( NLP ) tasks and retrieval-augmentedgeneration ( RAG ) systems. Expertise in embedding models, indexing techniques, and reranking methods. Familiarity with frameworks and libraries like HuggingFace and LangChain. Deployment: Proficiency with deploying large language … tuning large language models (LLMs). Interest or experience with MCP , A2A , or AutoGen . Keeps up to date with the latest trends in RAG solutions, agentic AI, and generative AI implementations. Behavioural Competencies: Accountability: Takes ownership and responsibility for tasks and outcomes. Proactiveness: Anticipates needs, takes initiative, and seeks More ❯
GPT-4, Claude, Gemini, and beyond) Knowledgeable of the latest developments in diffusion models and other generative frameworks for both text and image generation Competent in Generative AI and language models to spearhead innovative initiatives that leverage cutting-edge techniques in NLP and AI Adept at applying advanced … and deployment in production Choose relevant computational tools for study, experiment, or trial research objectives Drive the development of innovative solutions for language generation, text synthesis, and creative content generation using the latest state … of-the-art techniques Develop and implement advanced Generative AI solutions such as intelligent assistants, Retrieval-AugmentedGeneration (RAG) systems, and other innovative applications Produce clear, concise, well-organized, and error-free computer programs with the appropriate technological stack Present results directly to stakeholders More ❯
build and evolve Generative AI (GenAI) proof-of-concepts (POCs) for clients using techniques like Retrieval-AugmentedGeneration (RAG) and intelligent agents. Support the transition of these POCs into scalable, production-ready solutions. C Contribute to the design and development of full-stack applications More ❯
cross-functional teams. Experimental Approach: A passion for rapid iteration, learning from experiments, and data-driven development. Preferred Qualifications Experience designing RAG (Retrieval-AugmentedGeneration) or CAG systems using vector databases and hybrid retrieval techniques. Knowledge of LLM security challenges, including prompt More ❯
in production. Strong background in LLMs, NLP, and conversational AI (e.g., GPT, Claude, Mistral, LLaMA, etc.) Expertise with frameworks like LangChain, Hugging Face, OpenAI, RAG pipelines, and vector databases (e.g., Weaviate, Pinecone, Chroma) Solid knowledge of AI system architecture, including model serving, monitoring, and optimization Strong programming skills in Python More ❯
API and database skills (e.g., PostgreSQL). ML/AI: ML model training and deployment expertise. AutoML know-how (e.g., AutoKeras). NLP and RAG skills (embedding, indexing). Familiarity with HuggingFace, LangChain. Deployment: LLM deployment (SGLang, TGI, vLLM). Linux/command-line fluency. Cloud deployment basics. Kubernetes/ More ❯
REST or GraphQL endpoints. • Build multi-tenant data models and role-based workflows. • Trigger emails and webhooks for status changes. *AI/Retrieval-AugmentedGeneration* • Wire existing prompts to an LLM API (OpenAI-compatible today, private model later). • Store embeddings in a vector … store and perform RAG look-ups. • Surface “explanation” JSON for every model decision. *Cloud hand-offs* • Deploy new services into the existing Terraform/ECS stack—extend, don’t rewrite. • Add CloudWatch alarms, log routes and parameter-store secrets where needed. *Quality & Ops* • Write unit and integration tests and set More ❯
Senior AI Engineer (Data/Python) | Fully Remote | Up to £100k AI-first Expert Networking Platform powering the next generation of entrepreneurship. Senior AI Engineer (Data/Python) you will take full ownership of their AI and Data strategy, leading on everything from recommender systems and NLP to … Python, Kafka, Recommender Systems, LLMs, Semantic Search, 3rd Party Data Integration What do you need? Hands-on experience with LLMs (prompt engineering, fine-tuning, RAG) Strong experience with complex data extraction and data sorting Knowledge of backend development for deploying models. FinTech or B2B marketplace experience (beneficial) What do you More ❯