Role Overview :

We are looking for a highly skilled Agentic AI / Generative AI Engineer to design, develop, and scale intelligent AI systems leveraging LLMs, RAG pipelines, and multi-agent architectures. The ideal candidate will have hands-on experience in building production-grade GenAI applications and deploying scalable AI solutions using modern frameworks and cloud platforms.

Key Responsibilities :

- Design and implement solutions using Large Language Models (LLMs) such as GPT, Claude, Gemini, etc.

- Develop advanced prompt engineering strategies to optimize model performance.

- Fine-tune and evaluate LLMs for domain-specific use cases.

- Build and optimize RAG pipelines integrating structured and unstructured data sources.

- Work with vector databases like FAISS, Pinecone for semantic search and retrieval.

- Improve retrieval accuracy, latency, and response quality.

- Design and develop Agentic AI workflows for autonomous task execution.

- Build multi-agent systems with task planning, orchestration, and tool usage.

- Implement frameworks like LangChain Agents / AutoGen / CrewAI / MCP-based systems.

- Develop scalable APIs using Python frameworks like FastAPI.

- Integrate LLM services into backend systems and enterprise workflows.

- Ensure system reliability, scalability, and performance optimization.

- Deploy AI solutions on Azure OpenAI / AWS Bedrock / GCP Vertex AI.

- Build secure, scalable, and cost-efficient architectures.

- Work with containerization (Docker, Kubernetes) for production deployment.

- Process large datasets for training, embedding, and retrieval.

- Optimize pipelines for latency, throughput, and cost efficiency.

- Implement monitoring and evaluation frameworks for GenAI systems.

- Work closely with product, data, and engineering teams to define AI solutions.

- Mentor junior engineers and guide best practices in GenAI development.

- Stay updated with latest advancements in AI, LLMs, and agentic frameworks.

Required Skills :

- Strong experience in Python development

- Hands-on with LLMs, Prompt Engineering, and RAG pipelines

- Experience with LangChain / LlamaIndex / Agent frameworks

- Knowledge of vector databases (FAISS, Pinecone, Weaviate)

- Experience with Agentic AI, Multi-agent systems, MCP (Model Context Protocol)

Cloud & Tools :

- Azure OpenAI / AWS Bedrock / GCP Vertex AI

- FastAPI / REST API development

- Docker, Kubernetes (good to have)

AI/ML Fundamentals :

- NLP concepts, embeddings, semantic search

- Model evaluation, fine-tuning, and optimization techniques

- Experience in building enterprise-grade GenAI applications

- Exposure to AI safety, guardrails, and responsible AI practices

- Prior experience in SaaS / B2B AI products

- Familiarity with CI/CD pipelines and MLOps tools

- Knowledge of Graph RAG / Knowledge Graphs

- Experience with streaming data pipelines

- Understanding of multi-modal AI (text, image, audio)

What We Offer :

- Opportunity to work on cutting-edge Agentic AI systems

- High-impact role in building next-gen AI products

- Collaborative and innovation-driven environment