Xebia
Website:
xebia.com
Job details:
Job Title : Lead Gen AI Engineer
Job location : Bengaluru
Exp : 8-14 years
Position Overview : We are looking for a highly skilled – AI/LLM Engineer with strong expertise in building and deploying enterprise-grade Generative AI and Agentic AI solutions. The ideal candidate should have deep hands-on experience in Python, LangChain, LangGraph, LangFlow, RAG architectures, LLM deployment, AI agents, MCP servers, tool integrations, and memory orchestration frameworks. This role requires strong engineering fundamentals, scalable system design capabilities, and experience taking AI products from prototype to production.
Key Responsibilities
- Design, develop, and deploy scalable AI/LLM-powered applications using modern GenAI frameworks.
- Build enterprise-grade Agentic AI systems leveraging:
- Multi-agent orchestration
- Tool calling
- Memory sharing
- Autonomous workflows
- MCP (Model Context Protocol) server integrations
- Develop advanced RAG (Retrieval Augmented Generation) pipelines with vector databases and semantic search.
- Build workflows using LangChain, LangGraph, and LangFlow for complex AI orchestration.
- Integrate LLMs with enterprise systems, APIs, databases, and third-party tools.
- Deploy and optimize open-source and commercial LLMs in production environments.
- Design prompt engineering strategies, context management, and reasoning workflows.
- Implement observability, monitoring, evaluation, and guardrails for AI systems.
- Work on scalable backend systems and microservices architecture using Python.
- Optimize inference performance, latency, and cost for AI workloads.
- Collaborate with product managers, architects, and cross-functional engineering teams to define AI solutions.
- Mentor junior engineers and contribute to architecture and technical design discussions.
- Drive best practices around coding standards, CI/CD, testing, security, and AI governance.
Required Skills & Experience
Core Skills
- Strong hands-on programming experience in Python
- Expertise in:
- LangChain
- LangGraph
- LangFlow
- Strong understanding of:
- Large Language Models (LLMs)
- Generative AI architectures
- Agentic AI systems
- Multi-agent orchestration
- AI memory frameworks
AI/LLM Engineering
- Experience in deployment and fine-tuning of LLMs
- Strong implementation experience with:
- RAG pipelines
- Embedding models
- Vector databases
- Semantic search
- Hands-on experience with:
- AI Agents
- MCP Server implementation
- Tool calling frameworks
- Memory sharing architectures
- Function calling
Click on Apply to know more.