Establish best practices for prompt optimization, response consistency, and output quality management.
AI Workflow Orchestration & Automation
Design and build scalable orchestration pipelines using frameworks such as LangGraph, LangChain, CrewAI, Semantic Kernel, or equivalent.
Develop reusable AI components, tools, agents, and workflow templates for enterprise adoption.
Implement multi-agent systems and autonomous workflows to support complex business use cases.
Prototyping & Business Enablement
Partner with business stakeholders to identify high-value AI opportunities.
Rapidly develop AI prototypes and MVP solutions using synthetic and enterprise datasets.
Convert prototypes into production-ready applications adhering to scalability, security, and reliability standards.
Cloud & Data Engineering
Build scalable GenAI architectures across AWS, GCP, and Snowflake platforms.
Leverage cloud-native AI services including Amazon Bedrock, SageMaker, Vertex AI, Snowflake Cortex AI, and related ecosystems.
Design robust RAG (Retrieval-Augmented Generation) architectures incorporating vector databases, embeddings, and semantic search.
Optimize model deployment, inference performance, and infrastructure cost efficiency.
Evaluation & Performance Optimization
Establish AI evaluation frameworks to measure accuracy, relevance, latency, safety, and business impact.
Develop benchmarking methodologies for comparing prompts, models, and workflows.
Define KPIs, observability frameworks, and monitoring strategies for GenAI applications.
Continuously improve model performance through prompt tuning, retrieval optimization, and workflow enhancements.
Bachelor's or Master's degree in Computer Science, Artificial Intelligence, Data Science, Engineering, or a related field.
8+ years of experience in software engineering, machine learning, data engineering, or AI solution development.
4+ years of hands-on experience with Generative AI, LLMs, and foundation models.
Strong experience designing enterprise GenAI solutions utilizing advanced LLM architectures and prompt frameworks.
Expertise in building scalable AI workflows, orchestration pipelines, and reusable AI components.
Proven ability to translate business requirements into production-ready AI solutions and prototypes using synthetic data.
Deep understanding of prompt versioning, prompt governance, guardrails, and controlled LLM outputs.
Strong knowledge of AI evaluation frameworks, benchmarking methodologies, and optimization techniques.
Experience with vector databases, embeddings, semantic search, and RAG architectures.
Strong proficiency in Python and modern AI/ML development frameworks.