AI Architect

About the Company

Nuaav is a boutique technology consulting firm focused on building innovative, scalable and secure technology solutions across Data Engineering, Artificial Intelligence and Product Engineering. We partner with global enterprises to solve complex business challenges through technology, engineering excellence and domain expertise.

About the Role

We are looking for a highly experienced Senior AI Engineer / AI Architect to architect, develop and deploy enterprise-grade AI solutions, with a strong focus on Generative AI, Agentic AI, Large Language Models (LLMs) and Retrieval-Augmented Generation (RAG).

The ideal candidate will combine strong hands-on engineering capabilities with solution architecture expertise, building intelligent, scalable and production-ready AI applications that integrate seamlessly with enterprise systems.

You will lead the technical design and implementation of AI-driven platforms, multi-agent workflows and intelligent automation solutions while working closely with engineering, product and business teams.

• AI Architecture & Solution Design: Design scalable, secure and production-ready AI architectures, including agentic systems, microservices and event-driven architectures.
• Generative AI & LLM Engineering: Build applications using LLMs, including GPT-4/4o, Claude and other foundation models, leveraging prompt engineering, model orchestration and context management.
• Agentic AI Development: Design and implement autonomous and multi-agent systems using frameworks such as LangGraph, LangChain and similar technologies.
• RAG & Knowledge Systems: Develop advanced RAG pipelines incorporating document ingestion, chunking, embedding generation, vector search, hybrid retrieval, reranking and contextual retrieval.
• Enterprise AI Integration: Integrate AI applications with enterprise platforms, APIs, databases and existing business workflows.
• Cloud & Deployment: Architect and deploy scalable AI solutions on AWS using services such as EC2, ECS, S3, Lambda and SageMaker.
• AI Engineering & Optimization: Drive improvements in model performance, response latency, token consumption, retrieval accuracy and overall application efficiency.
• LLMOps & Observability: Implement AI evaluation frameworks, monitoring, tracing, guardrails and observability to ensure reliability, accuracy and responsible AI deployment.
• Technical Leadership: Establish architecture standards, conduct technical reviews, mentor engineering teams and drive engineering best practices.
• Client & Business Collaboration: Translate complex business requirements into scalable AI solutions and participate in technical discussions, solution design and architecture decisions.

Required Technical Skills

1. Generative AI & LLMs

• Strong hands-on experience with LLMs such as OpenAI GPT, Claude, Llama or equivalent models.
• Prompt engineering, context engineering, function calling and structured outputs.
• LLM orchestration using LangChain, LangGraph or similar frameworks.
• Experience with model selection, evaluation, fine-tuning concepts and inference optimization.

2. Agentic AI & Multi-Agent Systems

• Hands-on experience building agentic AI applications and autonomous workflows.
• Multi-agent orchestration, tool calling, planning, memory management and workflow execution.
• Experience with LangGraph, CrewAI, AutoGen or equivalent frameworks.
• Understanding of human-in-the-loop workflows and AI guardrails.

3. RAG & Vector Databases

• Strong expertise in designing and implementing enterprise-grade RAG architectures.
• Experience with vector databases such as Pinecone, Weaviate, Qdrant, OpenSearch or Neo4j.
• Knowledge of embeddings, semantic search, hybrid retrieval, reranking and knowledge graphs.
• Experience improving retrieval relevance, grounding and reducing hallucinations.

4. Programming & Backend Engineering

• Strong Python programming skills.
• Experience with FastAPI, REST APIs and GraphQL.
• Strong understanding of microservices, distributed systems and event-driven architectures.
• Experience with Kafka, RabbitMQ or similar messaging technologies.
• Working knowledge of SQL and NoSQL databases.

5. AWS, DevOps & Deployment

• Hands-on experience deploying production AI applications on AWS.
• Exposure to EC2, ECS, S3, Lambda and SageMaker.
• Docker, Kubernetes and CI/CD pipelines.
• Experience with GitHub Actions, Jenkins or equivalent tools.
• Understanding of scalable cloud architecture, security and infrastructure optimization.

6. AI Quality, Security & Observability

• Experience with LLM evaluation, model monitoring and performance benchmarking.
• Familiarity with tools such as LangSmith, OpenTelemetry, Arize or equivalent.
• Knowledge of responsible AI, prompt injection prevention, data privacy and security guardrails.
• Experience monitoring hallucination, faithfulness, relevance and response quality.

Preferred Qualifications

• Experience building enterprise AI solutions in production environments.
• Exposure to financial services, insurance, banking or other regulated industries.
• Experience with document intelligence, intelligent automation and enterprise knowledge management.
• Understanding of compliance, auditability, data governance and secure AI architectures.
• Experience leading architecture discussions and mentoring engineering teams.

Experience & Qualifications

• 10–14+ years of overall software engineering and architecture experience.
• At least 4–5 years of relevant experience in AI/ML, Generative AI, NLP or intelligent automation, with substantial recent hands-on GenAI/Agentic AI development.
• Demonstrated experience architecting and deploying production-grade AI applications.
• Strong technical ownership, problem-solving and stakeholder management capabilities.
• Bachelor's or Master's degree in Computer Science, Engineering or a related discipline.

What We Are Looking For

We are looking for an engineering professional who can go beyond building AI prototypes and take complete ownership of enterprise AI solutions — from architecture and development to deployment, optimization and production monitoring.

The candidate should be equally comfortable discussing AI architecture with clients, writing production-quality Python code, building multi-agent workflows and guiding engineering teams.

At Nuaav, you will have the opportunity to build next-generation AI solutions and solve complex enterprise challenges using Generative AI and Agentic AI technologies.