GenAI Solutions Architect

About the Role

Join our dynamic AI delivery team as a GenAI Solutions Architect. In this role, you will be responsible for designing and developing large language model (LLM) systems, transforming theoretical concepts into practical applications that enhance search, summarization, knowledge assistance, and automation for our enterprise clients.

This position emphasizes hands-on execution. You will collaborate with product managers, engineers, and specialists in AI to deploy scalable solutions effectively. Your focus will be on delivering real systems that users depend on, rather than getting bogged down in research or theoretical model development.

Benefits & Growth Opportunities:

· Competitive salary complemented with performance bonuses
· Extensive health insurance coverage
· Professional development opportunities and certification assistance
· Chances to engage with innovative AI projects
· Opportunities for international exposure and travel
· Flexible work arrangements
· Pathways for career advancement in a rapidly expanding AI organization

This role provides a significant opportunity to influence the trajectory of AI implementation while working alongside a skilled team at the cutting edge of technological advancements. The ideal candidate will be instrumental in steering our company's success in delivering transformative AI solutions for our clients.

What You’ll Do

• Architect comprehensive GenAI systems, focusing on prompt chaining, memory strategies, token budgeting, and embedding pipelines.
• Design and enhance RAG (Retrieval-Augmented Generation) workflows utilizing tools such as LangChain, LlamaIndex, and vector databases (FAISS, Pinecone, Qdrant).
• Assess tradeoffs involving zero-shot prompting, fine-tuning, LoRA/QLoRA, and hybrid methods to align solutions with user objectives and constraints.
• Integrate LLMs and APIs (e.g., OpenAI, Anthropic, Cohere, Hugging Face) into real-time applications with a focus on latency, scalability, and observability.
• Collaborate with cross-functional teams to translate complex GenAI architectures into reliable, maintainable features that facilitate product delivery.
• Draft and assess technical design documents while remaining actively engaged in implementation decisions.
• Deploy systems into production adhering to industry best practices encompassing version control, API lifecycle management, and monitoring (e.g., hallucination detection, prompt drift).

What You’ll Bring

• Demonstrated experience in developing and deploying GenAI-powered applications, particularly in enterprise or regulated settings.
• Thorough knowledge of LLMs, vector search, embeddings, and GenAI design patterns (including RAG, prompt injection protection, tool utilization with agents).
• Expertise in Python and familiarity with frameworks and tools such as LangChain, Transformers, Hugging Face, and OpenAI SDKs.
• Experience with vector databases like FAISS, Qdrant, or Pinecone.
• Knowledge of cloud infrastructure (AWS, GCP, or Azure) and core MLOps concepts (CI/CD, monitoring, containerization).
• A results-oriented mindset to balance speed, quality, and feasibility in fast-paced projects.

Nice to Have

• Experience in building multi-tenant GenAI platforms.
• Understanding of enterprise-grade AI governance and security protocols.
• Familiarity with multi-modal architectures (e.g., text + image or audio).
• Knowledge of cost-optimization tactics for LLM inference and token utilization.

This Role Is Not For

• Research scientists concentrating on academic model development without practical delivery experience.
• Data scientists who lack familiarity with vector search, LLM prompt engineering, or system architecture.
• Engineers who have not implemented GenAI products in production environments.