Solution Architect – Python

We are seeking a Solution Architect specializing in Python and GenAI to design and build production-grade GenAI solutions for enterprise clients.

Join our Solution Architecture team to lead technical discovery, develop reusable accelerators, and define best practices for LLM applications. Apply now to contribute to cutting-edge GenAI projects and help clients achieve transformative results.

Responsibilities

• Design end-to-end GenAI architectures including RAG, Agents, and Multi-Agent Systems for enterprise clients
• Build reusable solution accelerators and reference implementations to standardize delivery
• Lead technical discovery sessions and provide hands-on guidance to engineering teams
• Define evaluation frameworks and establish best practices for large language model (LLM) applications
• Collaborate with cross-functional teams to ensure scalable and maintainable system designs
• Implement microservices architectures using design patterns and modern frameworks
• Oversee integration of cloud infrastructure components such as AWS, Azure, or GCP
• Manage containerization and orchestration using Docker and Kubernetes
• Evaluate and select vector databases like Pinecone, Weaviate, or Chroma for GenAI solutions
• Apply LLMOps practices and monitoring to optimize production deployments
• Support prompt management and RAG evaluation to enhance application accuracy
• Contribute to knowledge sharing and mentoring within the architecture group
• Ensure production-grade code quality in Python applications
• Drive continuous improvement in system design and solution scalability

Requirements

• Strong solution architecture and system design experience with 9-14 years in software development
• Expert Python programming skills with production-grade code quality
• Proficient in microservices, design patterns, FastAPI, Redis, Elasticsearch, and Kafka
• Extensive GenAI application development experience including Agents, MCP, RAG, Agentic RAG, and GraphRAG
• Deep knowledge of LangGraph, LangChain, and orchestration frameworks
• Practical experience in LLM evaluation, RAG evaluation, and prompt management
• Proven track record delivering scalable, production GenAI applications
• Experience with cloud platforms such as AWS, Azure, or GCP
• Familiarity with container technologies Docker and Kubernetes
• Knowledge of vector databases including Pinecone, Weaviate, or Chroma
• Understanding of LLMOps practices and monitoring tools
• Excellent leadership skills to guide engineering teams
• Ability to work collaboratively in a client-facing environment
• Strong written and verbal English communication skills (B2+)

Nice to have

• Background in traditional machine learning including feature engineering, model training, and evaluation
• Experience with knowledge graphs and fine-tuning techniques
• Prior consulting or client-facing role experience