Gramener Technology - Technical Lead/Architect - Python/Generative AI

Roles and Responsibilities :

- Lead the end-to-end architecture and design of Python-based applications integrated with GenAI capabilities.

- Translate business and product requirements into modular, scalable, and maintainable technical solutions.

- Guide and mentor backend, infrastructure, and MLOps teams in implementing architecture blueprints.

- Evaluate and recommend the right mix of tools, frameworks, and platforms including LLM providers, vector databases, and cloud-based ML services.

- Ensure the security, scalability, and performance of all deployed systems.

- Stay current with advancements in GenAI, and proactively bring relevant capabilities into solution design.

Skills And Qualifications :

- 10+ years of experience in software engineering, with a minimum of 4 years in a technical leadership or architecture role.

- Proven track record in building robust Python-based backend systems, using frameworks such as FastAPI, Flask, or Django.

- Expertise in microservices architecture, distributed system design, and integration patterns.

- Strong familiarity with cloud platforms such as AWS, Azure, or GCP, and practical knowledge of AI/ML services like SageMaker, Vertex AI, or Azure ML.

- Architectural experience with vector databases (e.g., Pinecone, FAISS, Weaviate, Qdrant) for semantic search and RAG pipelines.

- Understanding of DevOps practices, including Docker, Kubernetes, and infrastructure as code.

- Knowledge of CI/CD processes, system security, and observability/monitoring frameworks.

GenAI & AI/ML Architecture Expertise :

- Sound understanding of GenAI system components, including LLM lifecycles, embedding generation, prompt orchestration, and RAG architectures.

- Ability to architect complete GenAI workflows, from context ingestion and enrichment to inference handling and post-processing.

- Familiarity with API orchestration, agent-based design patterns, and semantic search strategies.

- Direct data science work isnt required, but a solid understanding of AI/ML engineering principles and pipeline design is essential to ensure the architecture supports model and data requirements