This role focuses on developing AI applications powered by large language models (LLMs), retrieval-augmented generation (RAG), Model Context Protocol (MCP) servers, and Agentic AI across the enterprise. Need someone with Langchain/LangGraph exp.
Seeking a highly skilled AI Engineer to design and build Generative and Agentic AI systems that transform how our company operates and serves customers. This role focuses on developing AI applications powered by large language models (LLMs), retrieval-augmented generation (RAG), Model Context Protocol (MCP) servers, and Agentic AI across the enterprise for internal and customer facing use cases.
The ideal candidate has strong experience with a modern AI/ML stack, including a profound Python experience, including AI relevant packages and tools, LLM architectures and frameworks, RAG, MCP, prompt engineering, use of AI tools, budling teams of AI agents, and production-grade AI systems design and development.
You will work closely with technology, data, and business teams to build scalable AI solutions that drive operational efficiency and innovation across the enterprise.
Key Responsibilities:
- Design, build, and deploy scalable LLM-powered applications, solutions, and digital products for customer support, business use cases, and internal productivity.
- Develop AI agents, Agentic Platforms, and Agentic AI systems capable of reasoning, planning, and executing multi-step workflows.
- Implement Retrieval-Augmented Generation (RAG) architectures and pipelines to leverage proprietary data, and internal knowledge bases.
- Build MCP servers, multi-connectivity enabled and multi-modal Agentic platforms, and AI assistants to support internal teams and customer facing.
- Integrate AI/ML solutions with enterprise systems, APIs, and data platforms.
- Design prompt strategies, evaluation frameworks, and guardrails to ensure accuracy, security, and regulatory compliance.
- Optimize LLM performance through fine-tuning, prompt engineering, and model orchestration.
- Develop MLOps and LLMOps pipelines for monitoring, evaluation, and continuous improvement of AI systems.
- Help in forming buy or build decisions and work with external vendors, consultants and internal teams to deliver scalable top-quality AI solutions timely.
- Stay up to date with emerging advancements in AI/ML, Generative AI, Agentinc frameworks, and model architectures.
Required Qualifications:
- Bachelor s or Master s degree in Computer Science, Artificial Intelligence, Machine Learning, Applied Mathematics, or related field.
- 2+ years of software engineering experience, including work with machine learning (ML) or AI systems.
- Hands-on experience building LLM-powered applications in production environments.
- Strong programming skills in Python, and familiarity with AI/ML relevant packages such as NumPy, Pandas, SciPy and Scikit-learn.
- Experience with LLM ecosystems such as:
- OpenAI / Anthropic / Google, Open-source LLMs
- Hugging Face
- LangChain, LlamaIndex, or similar orchestration frameworks
- Experience building RAG pipelines and working with vector databases.
- Understanding of prompt engineering, embeddings, and model evaluation.
- Experience building APIs, MCPs, and scalable backend services.
- Experience with Claude Code, Codex, Cursor, GitHub Copilot, or similar.
- Ability to collaborate with cross-functional teams.
- Passion for technology and AI.
Preferred Qualifications:
- Experience building AI agents, agentic platforms, or autonomous workflows.
- Familiarity with agent frameworks (LangGraph, AutoGen, CrewAI, Semantic Kernel, Frontier, etc.).
- Experience with fine-tuning LLMs or parameter-efficient training methods (LoRA, PEFT).
- Experience with cloud-based AI infrastructure (AWS, Azure, or Google Cloud Platform).
- Familiarity with Java, JS, and Java applications and environments.
- Experience with MLOps / LLMOps tools and evaluation pipelines.
Experience implementing AI governance, observability, and guardrails.