Solution Architect – Python with GenAI

About the Role

Join our team as a Solution Architect focused on Python and Generative AI, responsible for designing and implementing enterprise-level GenAI solutions. You will spearhead technical explorations, craft reusable components, and set best practices for large language model (LLM) based applications, driving transformative outcomes for clients.

Key Responsibilities

• Architect comprehensive GenAI solutions including Retrieval-Augmented Generation (RAG), Agent frameworks, and Multi-Agent Systems tailored for enterprise needs.
• Develop and maintain reusable acceleration tools and standard reference implementations to promote consistency in solution delivery.
• Lead technical discovery workshops and provide practical support to development teams.
• Establish evaluation frameworks and define best practices for LLM implementations.
• Collaborate with diverse teams to design scalable and maintainable architectures.
• Implement microservices using appropriate design patterns and latest frameworks.
• Integrate cloud services across AWS, Azure, or Google Cloud Platform efficiently.
• Manage containerization and orchestration using Docker and Kubernetes technologies.
• Assess and select vector databases such as Pinecone, Weaviate, or Chroma for GenAI applications.
• Apply LLM operations (LLMOps) practices and monitoring to maximize deployment effectiveness.
• Support prompt engineering and retrieval augmented generation (RAG) evaluation to improve accuracy.
• Contribute to team knowledge sharing and mentorship within the architecture group.
• Ensure Python code deployed in production adheres to high quality standards.
• Continuously enhance system design and solution scalability.

Required Qualifications

• 9 to 14 years of experience in software development with strong background in solution architecture and system design.
• Expertise in Python programming with proven ability to deliver production-quality code.
• Strong familiarity with microservices architecture, design patterns, FastAPI framework, Redis, Elasticsearch, and Kafka.
• Extensive hands-on experience developing GenAI applications, including usage of Agents, MCP, RAG, Agentic RAG, and GraphRAG methodologies.
• Deep understanding of LangGraph, LangChain, and orchestration frameworks.
• Practical knowledge in conducting LLM evaluations, RAG assessments, and prompt management techniques.
• Experience delivering scalable, production-grade GenAI solutions.
• Proficiency with cloud environments such as AWS, Microsoft Azure, or Google Cloud Platform.
• Competence in Docker containerization and Kubernetes orchestration.
• Knowledge of vector databases like Pinecone, Weaviate, or Chroma.
• Familiarity with LLMOps and associated monitoring tools.
• Leadership capabilities to guide and mentor engineering teams.
• Strong collaboration skills suitable for client engagement settings.
• Excellent verbal and written English communication skills, at least B2 level.

Desirable Skills

• Background in classical machine learning including feature engineering, model training, and evaluation.
• Experience with knowledge graph technologies and model fine-tuning procedures.
• Previous exposure to consulting or client-facing roles.