GenAI Technical Architect

GenAI Technical Architect

Experience Level: - 10+ years overall IT experience, with 3+ years in AI/GenAI/LLM based solution architecture.

• Should have strong technical expertise in Python, hands-on experience with at least one GenAI framework (LangGraph, LangChain, or Google AI Development Kit), and strong working knowledge of one hyperscaler platform (Google Cloud, Azure, or AWS).
• The associate should lead solution design, integrating LLMs into enterprise workflows, mentoring team members, and driving production-grade implementation of GenAI use cases.
• Good knowledge of MLOps or DevOps to automate model deployment, versioning, and monitoring.

Key Responsibilities:

Architecture & Design.

• Design modular, scalable GenAI architectures leveraging LLMs, RAG, LangChain, LangGraph, Google ADK or Cortex Agents.
• Define architecture patterns for multi-agent systems, context-aware pipelines, and hybrid reasoning flows.
• Integrate LLMs (e.g., Llama, Gemini, GPT, Claude) into enterprise systems and custom applications.
• Develop reusable prompt orchestration and workflow frameworks.
• Establish standards for vector database (e.g., ChromaDB, Pinecone, FAISS, Weaviate, Vertex AI Matching Engine) usage, embeddings, and context retrieval.
• Architect scalable and secure GenAI microservices leveraging cloud-native components.

Development & Implementation.

• Lead Python-based development efforts for building prompt orchestration, tool agents, and data pipelines.
• Develop and deploy APIs or microservices integrating LLMs with enterprise data sources.
• Design and deploy LLM-based microservices with robust error handling, observability, and scalability.
• Integrate custom models, open-weight models (e.g., Llama, Mistral), and API-based models (e.g., GPT, Claude, Gemini).
• Lead the end-to-end RAG lifecycle ingestion, embedding, retrieval, generation, and evaluation.
• Implement prompt optimization, context management, and model performance tuning.

Cloud Integration.

• Architect, deploy and monitor GenAI workloads on one hyperscaler:
• GCP (Vertex AI, Document AI, AlloyDB, BigQuery, Cloud Run)
• Azure (OpenAI Service, Cognitive Search, Azure ML)
• AWS (Bedrock, SageMaker, Lambda, API Gateway)
• Manage cloud infrastructure for scaling AI models, ensuring cost efficiency and compliance.

Collaboration & Leadership.

• Lead a small team of AI engineers and developers.
• Partner with product and data teams to identify AI-driven business opportunities.
• Conduct code reviews, enforce best practices, mentor development teams on AI/ML implementation best practices.
• Review and optimize system designs for cost efficiency and latency performance.
• Contribute to governance, model safety, and compliance frameworks.
• Collaborate closely with product owners, data engineers, and business stakeholders to translate business needs into technical requirements.
• Contribute to internal GenAI capability building and reusable assets for the organization.

Research & Innovation.

• Stay updated on LLM research, agentic frameworks, and GenAI trends.
• Protopye and evaluate multi-agent architectures, prompt optimization, and LLMOps pipelines.
• Experiment with prompt engineering, fine-tuning, and model evaluation metrics.

Required Skills & Experience:

Core Technical Skills.

• Python (advanced proficiency; ability to build APIs, pipelines, and modular frameworks).
• Hands-on experience with RAG systems, vector databases (FAISS, Pinecone, Chroma, Weaviate, or Snowflake Cortex Search).
• Hands-on with at least one GenAI framework:
• LangChain, LangGraph, or Google ADK (AI Development Kit).
• Solid understanding of LLMs (OpenAI, Anthropic, Meta, Mistral, Gemini, etc.) and token optimization strategies
• Experience designing multi-agent or autonomous AI workflows.
• Expertise with LLM integration (OpenAI API, Gemini API, Ollama, Hugging Face, etc.).
• Experience with RAG, embeddings, and vector databases.
• Familiarity with PEFT, LoRA, or prompt fine-tuning approaches.
• Experience designing scalable microservices and event-driven architectures.
• Proven experience in production deployment, load balancing, and monitoring AI workloads.
• Knowledge of data engineering concepts pipelines, ingestion, metadata, and data APIs.
• Familiarity with front-end integration (Streamlit, Gradio, or custom dashboards).
• Cloud / Hyperscaler Expertise (at least one required)
• Google Cloud Platform (GCP) Vertex AI, Document AI, BigQuery, AlloyDB, Cloud Run, IAM
• Azure Azure OpenAI, Cognitive Search, Azure ML, Azure Functions
• AWS Bedrock, SageMaker, Lambda, API Gateway, DynamoDB

Soft skills.

• Strong analytical and problem-solving mindset.
• Excellent communication and stakeholder management skills.
• Proven ability to lead technical discussions and drive cross-functional alignment.

Other Desirable Skills.

• Knowledge of REST APIs, JSON, and FastAPI/Flask frameworks.
• Familiarity with data governance, PII handling, and AI ethics principles.
• Understanding of Docker/Kubernetes, CI/CD, and Git-based version control.
• Exposure to front-end integration with AI chat agents (React, Streamlit, Gradio, etc.) is a plus.
• Offshore, open to all TCS ODC located areas