AI Specialist ( LLMOps & Applied GenAI )

Roles and Responsibilities
Design, test, and refine prompts to optimize LLM performance across diverse tasks and domains.Build and maintain a library of prompt templates and reusable components.Collaborate with engineers, analysts, and business teams to embed prompt engineering into broader AI workflows.Analyse model outputs and user feedback to iteratively improve prompt accuracy, consistency, and relevance.Monitor developments in the fields of prompt engineering, generative AI, and LLM capabilities to inform internal practices.Contribute to documentation, internal guidelines, and knowledge-sharing initiatives related to prompt engineering.

Required Background
Demonstrable experience with prompt writing and LLM fine-tuning.Skilled in writing effective test cases for validation and performance checks.Basic data analysis capabilities, with proficiency in tools such as SQL and Excel.Strong problem-solving skills with a keen eye for detail.Excellent communication and collaboration skills, with the ability to work across cross-functional teams.Quick learner with a proactive mindset and an interest in emerging AI technologies.

Ideal Background
Design and deliver LLM-powered features with robust LLMOps. Choose models (OpenAI, Google, Anthropic, open-source), build RAG pipelines with vector stores, implement evaluation harnesses, guardrails, and safety checks. Optimise prompts, latency, cost, and quality; deploy services (vLLM/Ray Serve) and track telemetry.prompt design, and practical GenAI applications. You'll play a key role in optimizing how large language models (LLMs) are used across various workflows, helping drive innovation and performance through effective prompt engineering.Generative AI: advanced expertise working with: LLMs/transformer models, AWS Bedrock, SageMaker, LangChainLLM Ops: putting models into production in the AWS ecosystemExperience productionizing ML/Gen AI services and working with complex datasets.Srong understanding of software development, algorithms, optimization, and scaling.Excellent communication and business analysis skills.Cloud engineering experience (AWS cloud services)SnowflakeSoftware development experience to consolidating all information from thousands of tables. We want to explore using GNAI (Generative Natural Language AI) to accelerate this process, as the current manual approach is very laborious. The desired outcome is to have a senior -level resource who can deliver a proof of concept within 8-10 weeks in parttime as well.

Prompt engineering & prompt templates
RAG architecture (chunking, retrieval, ranking)Evaluation (groundedness, factuality) & guardrailsServing & scaling (vLLM/Ray), latency/cost tuningData governance, privacy, and security

Education-Bachelors/Masters in CS/AI/Statistics or equivalent.