In the role of Lead / Staff AI Engineer at TresVista, you will be responsible for owning the architecture, standards, and long-term direction of generative AI systems. Your role will involve designing systems that scale across teams, ensuring technical excellence, and transforming generative AI from experimentation into a reliable, reusable capability for the organization. Additionally, you will build intelligent agents from scratch, handle prompt design, retrieval pipelines, model fine-tuning, deployment in a secure cloud environment, implementing caching strategies, backend integration, and prototyping user interfaces for internal and client testing. This role requires deep technical skills, autonomy, and a passion for applying AI solutions in practical scenarios. You will have significant technical authority and will play a crucial role in shaping the future of operations at TresVista.
Key Responsibilities:
• Define and own the end-to-end architecture for generative AI systems across multiple use cases and teams• Establish and enforce standards for RAG, agent architectures, prompt and version management, evaluation, observability, and deployment• Make decisions on building, buying, fine-tuning, or replacing models, tools, and frameworks based on technical and business constraints• Design, evolve, and govern shared AI platforms, including reusable RAG pipelines, agent orchestration frameworks, prompt management systems, and evaluation/monitoring infrastructure• Drive reuse and standardization to eliminate one-off AI solutions and reduce long-term technical debt• Architect complex AI workflows, including multi-agent systems, tool orchestration, and long-running or asynchronous tasks• Design AI systems resilient to hallucinations, noisy inputs, partial failures, and model degradation• Optimize AI systems for latency, cost, reliability, scalability, and explainability at production scale• Lead technical design reviews, act as a technical authority, and resolve complex architectural and implementation challenges• Mentor and elevate the technical capabilities of senior and junior engineers across the generative AI stack• Define and enforce guardrails for data security, privacy, compliance, and responsible AI usage• Proactively identify model risks, operational failure modes, and scaling bottlenecks• Translate long-term business and product goals into concrete, extensible AI platform capabilities• Design, build, and optimize retrieval-augmented generation (RAG) pipelines using vector databases (e.g., Qdrant, Pinecone, FAISS) to power semantic search and intelligent document workflows• Fine-tune and adapt LLMs using Hugging Face Transformers, LoRA/PEFT, DeepSpeed, or Accelerate where domain adaptation is required• Integrate knowledge graphs (e.g., Neo4j, AWS Neptune) into agent pipelines for enhanced context, reasoning, and relationship modeling• Implement cache-augmented generation strategies (semantic caching, Redis, vector similarity) to reduce latency, cost, and output inconsistency• Build and maintain scalable backend services using FastAPI or Flask and support lightweight user interfaces or prototypes using Streamlit, Gradio, or React when neededQualifications Required:
• Deep technical skills in AI, machine learning, and data science• Experience in building and deploying AI systems in a production environment• Proficiency in working with generative AI models and frameworks• Strong knowledge of backend development and user interface prototyping• Ability to mentor and lead technical teams effectively• Understanding of data security, privacy, compliance, and responsible AI usage guidelines• Proven track record of solving complex technical challenges and driving innovation in AI technologies In the role of Lead / Staff AI Engineer at TresVista, you will be responsible for owning the architecture, standards, and long-term direction of generative AI systems. Your role will involve designing systems that scale across teams, ensuring technical excellence, and transforming generative AI from experimentation into a reliable, reusable capability for the organization. Additionally, you will build intelligent agents from scratch, handle prompt design, retrieval pipelines, model fine-tuning, deployment in a secure cloud environment, implementing caching strategies, backend integration, and prototyping user interfaces for internal and client testing. This role requires deep technical skills, autonomy, and a passion for applying AI solutions in practical scenarios. You will have significant technical authority and will play a crucial role in shaping the future of operations at TresVista.Key Responsibilities:
• Define and own the end-to-end architecture for generative AI systems across multiple use cases and teams• Establish and enforce standards for RAG, agent architectures, prompt and version management, evaluation, observability, and deployment• Make decisions on building, buying, fine-tun