Senior Specialist - Data Sciences

LTM is looking for a highly skilled GenAI Engineer to design, build, and operationalize next-generation AI solutions. The role involves leveraging Large Language Models and AI agents, integrating machine learning models, and developing data engineering pipelines to deliver scalable AI systems.

Responsibilities:

• Design develop and deploy LLMpowered applications using leading foundation models OpenAI Azure OpenAI Anthropic opensource LLMs
• Build LLMbased AI agents capable of multistep reasoning tool use orchestration and autonomous workflows
• Implement and optimize agent frameworks LangChain LlamaIndex Semantic Kernel AutoGen CrewAI etc
• Engineer robust prompting strategies memory mechanisms and toolaugmented reasoning
• Design and implement RetrievalAugmented Generation RAG architectures
• Build embedding pipelines using vector databases FAISS Pinecone Weaviate Azure AI Search Chroma
• Optimize document ingestion chunking strategies metadata management and reranking
• Ensure accuracy relevance and performance of AIgenerated responses
• Apply practical ML concepts including classification clustering ranking and similarity search where applicable
• Integrate traditional ML models with LLMbased systems for hybrid AI solutions
• Evaluate finetune and test models using appropriate performance metrics
• Develop and maintain data pipelines for structured and unstructured data using Python and SQL
• Work with large datasets APIs and streamingbatch processing frameworks
• Ensure data quality lineage observability and governance within AI workflows
• Build CICD pipelines for AI and ML workloads including model versioning and automated testing
• Deploy AI services in containerized environments Docker Kubernetes
• Implement monitoring for model performance drift latency and cost
• Ensure security access control and compliance for AI systems
• Design and deploy AI solutions on cloud platforms such as AWS Azure or GCP
• Leverage managed AIML services serverless components and scalable infrastructure
• Optimize cost performance and reliability of AI workloads
• Partner with product platform and business teams to translate requirements into AI solutions
• Document architectures design decisions and operational runbooks
• Provide guidance on GenAI best practices risks and responsible AI usage