Job Description :

We are looking for an AI Technical Lead with 6 to 11 years of experience to design and deliver enterprise-grade AI solutions using Generative AI, Multi-Agent Systems, RAG, MCP, and LLM fine-tuning. The ideal candidate should combine strong hands-on expertise in AI engineering and architecture with the ability to lead technical teams and drive end-to-end enterprise AI initiatives.

Key Responsibilities :

- Design and define scalable AI architectures for enterprise use cases involving LLMs, RAG, Multi-Agent Systems, and AI-powered applications.

- Architect and develop Multi-Agent Systems with effective agent orchestration, tool integration, memory, and workflow management.

- Design and implement RAG pipelines, including document ingestion, chunking, embeddings, vector search, retrieval, reranking, and context management.

- Build and integrate solutions using Model Context Protocol (MCP) and other mechanisms for connecting AI models with enterprise tools, systems, and data sources.

- Design and implement LLM fine-tuning and model adaptation strategies based on business requirements and domain-specific use cases.

- Apply context engineering techniques to improve model accuracy, relevance, reliability, and response quality.

- Develop scalable AI applications and supporting data pipelines using Python and modern AI/ML frameworks.

- Design knowledge graphs and structured knowledge representations to support intelligent retrieval and reasoning.

- Integrate LLMs with enterprise applications, APIs, databases, and external tools.

- Establish practices for prompt engineering, evaluation, observability, guardrails, security, and responsible AI.

- Drive AI solution deployment across cloud and enterprise environments with focus on scalability, performance, reliability, and cost optimization.

- Lead technical discussions, architecture reviews, and design decisions across AI engineering teams.

- Mentor engineers and provide technical direction on AI architecture, development, and deployment practices.

- Collaborate with product, data, engineering, security, and business stakeholders to translate business requirements into scalable AI solutions.

- Evaluate emerging AI technologies and frameworks and identify opportunities to improve enterprise AI capabilities.

Required Skills & Experience:

- 6-11 years of experience in AI/ML, software engineering, or related technical domains, with significant hands-on experience in Generative AI.

- Strong hands-on experience with Multi-Agent Systems, RAG, MCP, and LLM-based application development.

- Experience with LLM fine-tuning, model adaptation, prompt engineering, and context engineering.

- Strong proficiency in Python and experience with AI/ML development frameworks.

- Strong understanding of LLM architecture, embeddings, vector databases, retrieval techniques, and AI application patterns.

- Experience designing enterprise AI architectures and taking solutions from proof of concept to production.

- Experience building scalable data and knowledge pipelines for AI applications.

- Good understanding of knowledge graphs, semantic search, and structured/unstructured data processing.

- Experience with LLM evaluation, monitoring, guardrails, and AI application performance optimization.

- Strong understanding of APIs, microservices, cloud platforms, and scalable deployment architectures.

- Proven ability to lead technical teams and drive architecture and engineering decisions.

- Strong communication, stakeholder management, and problem-solving skills.

Preferred Skills :

- Experience with frameworks such as LangChain, LangGraph, LlamaIndex, Semantic Kernel, or similar.

- Experience with MCP servers, tools, and enterprise integrations.

- Hands-on experience with vector databases such as Pinecone, Milvus, Weaviate, pgvector, or equivalent.

- Experience with cloud AI platforms such as AWS Bedrock, Azure OpenAI, or Google Vertex AI.

- Exposure to MLOps, CI/CD, Docker, Kubernetes, and production AI observability.

- Experience delivering AI solutions in large enterprise environments.