Role: Senior Generative AI Engineer (Agentic AI)
Location: India (Remote)
About The Role
Our client, with a distributed engineering workforce of
400+ professionals across the US, Canada, UAE, India, and Pakistan, is seeking an experienced
Senior Generative AI Engineer with strong expertise in
Agentic AI systems.
This opportunity is best suited for professionals with
712+ years of software engineering and AI/ML experience who have transitioned into building
LLM-powered autonomous systems and intelligent agents. The ideal candidate will have practical experience working with frameworks such as
LangGraph, CrewAI, LangChain, AutoGPT, Semantic Kernel, or other comparable technologies for building agent-driven AI applications.
Key Responsibilities
- Design and develop autonomous AI applications using modern LLM frameworks such as LangGraph, CrewAI, AutoGPT, Semantic Kernel, or similar platforms
- Build and architect multi-agent AI systems capable of solving complex enterprise workflows
- Connect AI agents with APIs, enterprise databases, internal systems, and external SaaS platforms
- Provide technical leadership and mentorship to engineering teams working across multiple global locations
- Improve system efficiency by optimizing context handling, memory usage, tool invocation, and cost management
- Develop scalable AI pipelines, reusable modules, and frameworks to support multiple GenAI initiatives
- Ensure all AI deployments adhere to enterprise security, privacy, and compliance standards
- Engage directly with clients, stakeholders, and technical leadership to align AI solutions with business objectives
Ideal Candidate Profile
- 7 to 15 years of professional experience in software engineering and AI/ML development
- Minimum 2+ years of hands-on experience building applications using Large Language Models
- Proven experience delivering Agentic AI solutions, beyond simple chatbot implementations
- Strong hands-on expertise with frameworks and techniques such as:
- LangChain, CrewAI, AutoGPT, ReAct, Semantic Kernel
- LLM providers including OpenAI, Claude, Gemini, Mistral, or Llama 2
- Embeddings and vector databases such as FAISS, Pinecone, or Weaviate
- Prompt engineering, Retrieval-Augmented Generation (RAG), and memory/context management
- Experience integrating AI systems with Python, Node.js, serverless architectures, and cloud platforms (AWS, GCP, or Azure)
- Demonstrated ability to lead engineering teams and collaborate with enterprise customers
- Strong communication, documentation, and stakeholder engagement skills
Why Join
- Contribute to large-scale Generative AI initiatives for UAE government entities
- Work on cutting-edge Agentic AI platforms and enterprise-grade AI solutions
- Collaborate with experienced engineering teams located across the US, Canada, UAE, India, and Pakistan
Skills: agents,multi-agent systems,fine tuning
