Team Lead/Senior Specialist - AI

1. GenAI Architecture & Technical Direction

• Architect scalable GenAI systems across content generation, business intelligence, recommendations, automation, and agentic workflows.
• Design multi-LLM and multi-agent systems using frameworks such as LangGraph, CrewAI, AutoGen, or Semantic Kernel.
• Define architecture patterns for RAG, tool calling, function calling, agent memory, context management, and workflow orchestration.
• Evaluate when to use LLM APIs, SLMs, fine-tuned models, retrieval-based systems, deterministic logic, or hybrid approaches.
• Create reusable AI system patterns, prompts, evaluation flows, and orchestration layers that can be used across products.

2. Agentic AI & Workflow Systems

• Lead the design and development of agentic AI systems that can reason, use tools, call APIs, manage state, and complete multi-step tasks.
• Build and improve multi-agent collaboration patterns for use cases such as digital marketing, SMB intelligence, content generation, brand analysis, and campaign automation.
• Design guardrails to reduce hallucination, improve factual grounding, and ensure predictable outputs.
• Work on agent memory, state persistence, workflow checkpoints, and task handoffs across AI components.

3. RAG, Fine-Tuning & Model Optimization

• Design and improve RAG pipelines using vector databases, embeddings, chunking strategies, metadata, reranking, and retrieval evaluation.
• Guide fine-tuning or supervised training workflows where needed for specific business use cases.
• Optimize model selection across OpenAI, Gemini, Anthropic, Hugging Face, and open-source models based on cost, latency, accuracy, and reliability.
• Define model-switching and fallback strategies for production systems.
• Improve prompt engineering, structured outputs, schema adherence, and response consistency.

4. AI Evaluation, Quality & Governance

• Define AI quality evaluation frameworks for generated content, summaries, recommendations, and agent outputs.
• Build or guide regression testing for prompts, model changes, workflow changes, and release readiness.
• Track performance indicators such as output quality, edit ratio, hallucination rate, latency, failure rate, and inference cost.
• Contribute to GenAI governance practices, including responsible AI, privacy, safety, and compliance.
• Work with Product and QA teams to define measurable acceptance criteria for AI outputs.

5. Light Deployment & Production Readiness

• Work with engineering and platform teams to ensure AI systems are deployable, observable, and maintainable in production.
• Provide hands-on support for packaging AI services using Python, FastAPI/Flask, Docker, and cloud environments when needed.
• Understand basic CI/CD, versioning, logging, monitoring, rollbacks, and environment management for AI services.
• Partner with DevOps or backend teams on deployment architecture, scaling, and reliability.
• Monitor and troubleshoot common production issues related to latency, model failures, API limits, rate limits, cost spikes, and degraded output quality.

This role should be comfortable with deployment conversations, but the primary expectation is AI system architecture and technical leadership, not full-time DevOps ownership. The lighter deployment expectation keeps it distinct from the earlier AI Platform Specialist role, which was more focused on Python deployment, Docker, cloud, CI/CD, monitoring, scaling, and rollbacks.

6. Technical Leadership & Cross-Functional Collaboration

• Mentor GenAI engineers and guide technical decision-making across AI initiatives.
• Collaborate with Product, Data Engineering, Software Engineering, QA, and AI Operations teams.
• Translate product requirements into AI architecture, implementation plans, and measurable outcomes.
• Review AI designs, prompts, workflows, evaluation outputs, and architecture decisions.
  • Communicate clearly with both technical and non-technical stakeholders.