AI Solutions Architect

Responsibilities

• Architect end-to-end GenAI systems, including prompt chaining, memory strategies, token budgeting, and embedding pipelines
• Design and optimize Retrieval-Augmented Generation (RAG) workflows using tools like LangChain, LlamaIndex, and vector databases (FAISS, Pinecone, Qdrant)
• Evaluate tradeoffs between zero-shot prompting, fine-tuning, LoRA/QLoRA, and hybrid approaches, aligning solutions with user goals and constraints
• Integrate LLMs and APIs (OpenAI, Anthropic, Cohere, Hugging Face) into real-time products and services with performance and scalability in mind
• Collaborate with cross-functional teams to deliver stable, maintainable features
• Write and review technical design documents and contribute actively to implementation decisions
• Deploy to production, following best practices for version control, API lifecycle management, and system monitoring (e.g., hallucination detection, prompt drift)

Requirements

• Proven experience building and deploying GenAI-powered applications, ideally in enterprise or regulated environments
• Deep understanding of LLMs, vector search, embeddings, and GenAI design patterns (RAG, prompt injection protection, tool use with agents)
• Proficiency in Python and experience with frameworks/libraries such as LangChain, Transformers, Hugging Face, and OpenAI SDKs
• Experience with vector databases (FAISS, Qdrant, or Pinecone)
• Familiarity with cloud infrastructure (AWS, GCP, or Azure) and core MLOps concepts (CI/CD, monitoring, containerization)
• Strong delivery mindset, able to balance speed, quality, and feasibility

Preferred Qualifications

• Experience building multi-tenant GenAI platforms
• Exposure to enterprise-grade AI governance and security standards
• Familiarity with multi-modal architectures (e.g., text + image or audio)
• Knowledge of cost-optimization strategies for LLM inference and token usage

Benefits

• Competitive salary and performance bonuses
• Comprehensive health insurance
• Professional development and certification support
• Opportunity to work on cutting-edge AI projects
• International exposure and travel opportunities
• Flexible working arrangements
• Career advancement opportunities in a rapidly growing AI company

About the Company

Deeplight is a rapidly growing AI company committed to developing real-world, production-ready Generative AI solutions for enterprise clients. Joining Deeplight means collaborating with talented professionals and playing a vital role in delivering transformative AI-powered products to clients across various industries.