At XTS we are redefining how learning content is created and delivered. We are seeking a highly skilled Tech Lead – AI & LLM Engineering to lead the design and development of next-generation AI systems leveraging Large Language Models (LLMs), Model Context Protocol (MCP), Agentic AI frameworks, and intelligent automation.
The ideal candidate will have deep expertise in LLM integration, fine-tuning, and orchestration, combined with strong system design and software engineering skills to build scalable, secure, and intelligent solutions for enterprise use cases.
Responsibilities
We’re entering a critical phase:
- Lead architecture and end-to-end design of AI-integrated systems using LLMs and modern AI frameworks.
- Develop, fine-tune, and deploy custom LLM models for domain-specific applications (retrieval, summarization, Q&A, automation, etc.).
- Integrate LLMs with existing products and workflows using APIs, vector databases, and orchestration frameworks.
- Implement Agentic AI workflows for autonomous task execution, decision-making, and context management.
- Work with Model Context Protocol (MCP) for building context-aware AI systems and multi-agent ecosystems.
- Design RAG (Retrieval-Augmented Generation) pipelines using vector databases (Pinecone, Chroma, FAISS, etc.).
- Collaborate with stakeholders to identify opportunities for AI enablement across platforms.
- Ensure data security, prompt safety, and governance in all AI solutions.
- Guide a cross-functional team of engineers and data scientists in developing production-grade AI applications.
- Research and evaluate emerging AI frameworks, APIs, and tools to enhance system capabilities.
Technical Skills & Expertise:
Core AI/LLM Skills:
- LLMs: GPT, Claude, Llama, Mistral, Gemini, etc.
- Fine-tuning & prompt engineering for domain-specific performance.
- RAG architecture, embeddings, and semantic search.
- Agentic AI frameworks (LangGraph, AutoGPT, CrewAI, or similar).
- MCP (Model Context Protocol) integration and context orchestration.
- LLMOps (deployment, monitoring, evaluation, and optimization).
Programming & Frameworks:
- Python (FastAPI, LangChain, LlamaIndex, HuggingFace Transformers).
- API integration & orchestration using REST / GraphQL.
- Knowledge of microservices, event-driven design, and containerization (Docker/Kubernetes).
Data & Infrastructure:
- Experience with Vector Databases (Pinecone, Chroma, Milvus, Weaviate).
- Cloud Platforms: AWS / Azure / GCP (preferred: AWS Sagemaker, Bedrock, Azure OpenAI).
- Familiarity with data pipelines, MLOps, and data governance best practices.
Additional Good-to-Haves:
- Experience with multimodal AI (vision + language).
- Familiarity with OpenAI Assistants API, MCP-based tools, or Anthropic ecosystem.
- Understanding of ethical AI, safety, and compliance standards.
Soft Skills & Leadership:
- Proven ability to lead and mentor technical teams in AI solution development.
- Strong analytical and architectural thinking.
- Excellent communication, documentation, and stakeholder management skills.
- Passion for innovation, research, and continuous learning in AI technologies.
Education:
- Bachelor’s or Master’s degree in Computer Science, Artificial Intelligence, or a related field.
- Certifications in AI/ML, LLMs, or Cloud AI Services are a plus.
Tech Stack: Large Language Models, Agentic AI, MCP, Design RAG, Cloud, Vector Database, Python, Fast API, Microservices, Docker, Kubernetes.
Expected Joining: Within a month.
