Overview

Our client is seeking an AI-focused Developer with strong hands-on experience in Generative AI, LLM-based application development, and Agentic AI solutions.

Responsibilities

• Our client is seeking an AI-focused Developer with strong
• experience in Generative AI, LLM-based application development, and Agentic AI solutions.
• Design, develop, implement, and deploy Agentic AI applications and autonomous AI workflows.
• Build production-ready Generative AI and LLM-powered applications.
• Develop scalable backend services using Python or TypeScript.
• Design and integrate RESTful APIs, GraphQL APIs, and microservices.
• Build LLM workflows using LangChain, LlamaIndex, LangGraph, or similar orchestration frameworks.
• Develop AI agents capable of tool calling, API integration, planning, memory, reasoning, retrieval, and multi-step task execution.
• Implement prompt-engineering techniques such as zero-shot prompting, few-shot prompting, structured outputs, and function/tool calling.
• Integrate vector databases such as Pinecone, ChromaDB, FAISS, or Weaviate.
• Work with embeddings, transformers, NLP pipelines, semantic search, retrieval mechanisms, and contextual data.
• Build and integrate RAG-based applications and enterprise knowledge assistants.
• Deploy AI applications using AWS Bedrock, SageMaker, Google Vertex AI, Azure OpenAI, or similar cloud platforms.
• Monitor, troubleshoot, and optimize Agentic AI and LLM applications for performance, accuracy, reliability, scalability, latency, and cost.
• Implement version control and deployment workflows using Git and CI/CD pipelines.
• Create clear technical documentation for application architecture, AI workflows, APIs, integrations, and deployment processes.
• Collaborate with engineering, product, data, and business stakeholders.

Qualifications

• Candidates should have practical experience building and deploying real-world Agentic AI solutions. Profiles with only theoretical knowledge, training, certifications, or proof-of-concept exposure in Agentic AI will not be considered.
• 4+ years of overall relevant software development / AI application development experience.
• 3+ years of hands-on experience in Generative AI and LLM-based application development.
• 2+ year of hands-on Agentic AI experience involving real-world project implementation and deployment — mandatory.
• Proven experience building AI agents, multi-step agentic workflows, tool-calling solutions, or autonomous AI systems.
• Strong proficiency in Python or TypeScript for AI-driven backend development.
• Strong experience developing and integrating RESTful APIs.
• Hands-on experience with LangChain, LlamaIndex, LangGraph, or similar LLM orchestration frameworks.
• Strong understanding of prompt engineering, including zero-shot, few-shot, structured prompting, function calling, tool calling, and structured outputs.
• Experience with vector databases such as Pinecone, ChromaDB, FAISS, or Weaviate.
• Understanding of NLP, embeddings, transformers, semantic search, retrieval techniques, and RAG architectures.
• Experience with at least one cloud AI platform such as AWS Bedrock, SageMaker, Google Vertex AI, or Azure OpenAI.
• Knowledge of REST, GraphQL, microservices, and scalable application architecture.
• Experience using Git and CI/CD pipelines.
• Strong analytical, debugging, and problem-solving skills.
• Excellent technical documentation, collaboration, and communication skills.

Nice to have

• Experience developing multi-agent systems or agent orchestration workflows.
• Hands-on experience with RAG architectures and enterprise knowledge assistants.
• Experience with agent frameworks such as LangGraph, AutoGen, CrewAI, or Semantic Kernel.
• Knowledge of agent memory, planning, reasoning, tool usage, state management, and human-in-the-loop workflows.
• Experience implementing LLM evaluation, observability, monitoring, guardrails, and responsible AI controls.
• Familiarity with Docker, Kubernetes, serverless architecture, and cloud-native deployments.
• Experience optimizing LLM applications for latency, token usage, reliability, scalability, and cost.
• Exposure to fine-tuning, model selection, AI application security, and access controls.