Description :

Senior AI Specialist (GenAI & Agentic AI)

Experience : 5-8 Years

Role Summary :

The Senior AI Specialist is a core technical leader responsible for the architecture and deployment of advanced Generative and Agentic AI systems. This role demands a specialist who has transitioned beyond simple LLM prompts into building complex Multi-Agent Systems and high-precision GraphRAG architectures. You will be responsible for the end-to-end AI lifecyclefrom fine-tuning models and designing vector databases to implementing autonomous agents using frameworks like LangGraph or AutoGen. Operating within a cloud-native environment (GCP/AWS/Azure), you will bridge the gap between raw data and production-grade AI, ensuring that solutions are not only innovative but also governed by rigorous Guardrails and LLM Evaluation frameworks.

Responsibilities :

- Design, implement, and deploy production-grade LLM models and Generative AI applications to solve complex business challenges.

- Architect and orchestrate Agentic AI frameworks and Multi-Agent Systems using tools such as LangGraph, AutoGen, and the Model Context Protocol (MCP).

- Develop advanced Retrieval-Augmented Generation (RAG) and GraphRAG systems, optimizing retrieval accuracy through sophisticated embedding strategies and vector databases like FAISS or Pinecone.

- Lead model optimization efforts, including the fine-tuning of large language models and the implementation of efficient prompt engineering techniques.

- Integrate AI solutions into enterprise ecosystems using FastAPI for high-performance, asynchronous service delivery.

- Implement robust AI Guardrails and comprehensive LLM Evaluation pipelines to ensure output reliability, safety, and business alignment.

- Design and manage cloud-based AI infrastructure on GCP, AWS, or Azure, leveraging native GenAI services (e.g., Vertex AI, Bedrock, or Azure OpenAI).

- Engineer complex ETL flows and SQL scripts to extract and preprocess large datasets for model training and retrieval context.

- Translate ambiguous business requirements into detailed technical AI roadmaps and scalable solution designs.

- Communicate complex technical concepts, such as agentic reasoning and vector space optimization, to both technical teams and non-technical stakeholders.

Technical Requirements :

- Bachelors or Masters degree in Computer Science, Artificial Intelligence, or a related quantitative field.

- 5-8 years of professional experience in AI/ML, with a significant focus on Generative AI and Agentic architectures.

- Agentic Mastery : Hands-on experience with LangGraph, AutoGen, LangChain, and developing autonomous agents with tool-calling capabilities.

- Vector & Graph Expertise : Proven proficiency with Vector Databases (Pinecone, FAISS, Milvus) and the implementation of GraphRAG for structured knowledge retrieval.

- Production Deployment : Solid experience deploying AI models into production, including the use of FastAPI and containerization.

- Cloud Infrastructure : Expertise in designing AI solutions on AWS, GCP, or Azure, utilizing their respective GenAI and data suites.

- Evaluation & Safety : Deep understanding of LLM Evaluations (Ragas, TruLens) and the implementation of Guardrails (NeMo Guardrails, Llama Guard).

- Data Engineering : Strong proficiency in SQL and designing ETL pipelines for large-scale data extraction and cleaning.

Preferred Skills :

- Experience with Fine-tuning techniques like PEFT, LoRA, and QLoRA for domain-specific model adaptation.

- Familiarity with the Model Context Protocol (MCP) for standardized agent-tool communication.

- Knowledge of advanced prompt engineering patterns (Chain-of-Thought, Tree-of-Thought).

- Background in MloPS for Generative AI, including versioning models and monitoring for LLM drift.

- Passion for staying abreast of rapid innovations in the open-source AI community.

- Strong analytical mind with a focus on solving non-linear problems through autonomous AI reasoning.