Lead / Manager Agentic AI Engineer - Claude Code & Codex

Blend360

3d

About The Position

Blend is seeking an experienced Lead or Manager, Agentic AI Engineer to design, build, and deploy production-grade AI agents. These agents will execute complex, multi-step workflows via natural language. The role involves integrating LLMs, agent orchestration frameworks, MCP tools, AI coding agents, context and harness engineering, APIs, and enterprise systems to create intelligent assistants capable of reasoning, tool usage, action execution, and result validation. The ideal candidate will have practical experience developing agentic workflows beyond simple chatbots or PoCs, coupled with strong software engineering skills and a track record of deploying AI solutions into production.

Requirements

• 5–10 years of experience in Data Science or AI/ML or Software Engineer out of which atleast 2 years in Generative AI and Agentic AI, with hands-on experience building production-grade AI applications and agentic systems.
• Strong development skills in Python and experience building APIs and AI services using FastAPI or similar frameworks, along with experience in context engineering and AI agent harness engineering, including agent instructions, application/task context, permissions, guardrails, retries, validation, automated verification, and context optimization.
• Experience with AI coding agents such as Claude Code, OpenAI Codex, or similar platforms , including repository context, agent instructions, automated testing, coding workflows, and verification.
• Hands-on experience with A2A, MCP (Model Context Protocol) , including developing or integrating MCP servers and connecting agents with enterprise tools, APIs, databases, and SaaS platforms.
• Hands-on experience with LLMs, agent orchestration, and multi-step/multi-agent workflows using frameworks such as LangGraph, LangChain, Semantic Kernel, AutoGen , or equivalent technologies.
• Strong understanding of agent architecture, tool/function calling, planning, task decomposition, state/memory management, dynamic tool invocation, and workflow orchestration .
• Experience with RAG, embeddings, vector databases, semantic search, chunking, reranking, and grounding , with knowledge of LLM-as-a-Judge and automated GenAI evaluation .
• Strong software engineering and cloud experience, including Git, CI/CD, Docker, databases/SQL, AWS/Azure/GCP , with familiarity with asynchronous programming, parallel processing, observability, and distributed systems.
• Strong understanding of LLM performance and production optimization , including hallucination mitigation, context windows, token usage, latency, caching, cost optimization, and monitoring.
• Demonstrated ability to build secure, scalable, production-ready AI solutions with measurable business impact beyond POCs .

Responsibilities

• Design and develop LLM-powered autonomous and semi-autonomous agents capable of executing complex, multi-step workflows.
• Build agent workflows using frameworks such as LangGraph, LangChain, Semantic Kernel, AutoGen, or similar technologies.
• Implement planning, task decomposition, tool selection, execution, observation, retry, and validation loops.
• Develop agents that can interact with enterprise applications, APIs, databases, and developer tools through natural language.
• Design and implement context engineering strategies that provide agents with the right instructions, task context, application state, tools, and relevant information at the right time.
• Develop AI agent harnesses that manage agent state, tool access, permissions, execution workflows, guardrails, retries, and verification.
• Engineer repository and application context for AI coding agents such as Claude Code, OpenAI Codex, or similar platforms.
• Develop effective agent instructions, project context, coding guidelines, workflows, and automated verification mechanisms to improve agent reliability and developer productivity.
• Optimize context usage to reduce unnecessary token consumption, latency, and LLM costs.
• Design and develop Model Context Protocol (MCP) servers and tools that enable agents to interact with enterprise applications and services.
• Integrate agents with Git, GitHub/GitLab, Artifactory, Slack, databases, APIs, CI/CD platforms, and other enterprise tools.
• Build secure tool-calling mechanisms with appropriate authentication, authorization, permissions, and human approval workflows.
• Develop reusable tools that enable agents to perform actions rather than simply generate responses.
• Integrate and orchestrate LLMs for reasoning, planning, content generation, code generation, and task execution.
• Work with commercial and open-source LLMs and select appropriate models based on quality, latency, cost, and task complexity.
• Implement prompt engineering and advanced context management strategies.
• Apply techniques such as structured outputs, function/tool calling, model routing, and model fallback strategies.
• Implement RAG where required, including document retrieval, embeddings, vector databases, reranking, and grounding.
• Design evaluation frameworks to measure agent task completion, tool-call accuracy, response quality, hallucination, reliability, and business outcomes.
• Implement LLM-as-a-Judge and automated evaluation pipelines for agentic and GenAI applications.
• Build regression testing and validation workflows for agent behavior.
• Implement guardrails, error handling, retry mechanisms, and human-in-the-loop controls for high-risk actions.
• Develop production-grade AI services using Python and FastAPI or similar frameworks.
• Deploy and operate agentic applications in cloud and enterprise environments.
• Design scalable architectures that support concurrent users, long-running agent workflows, and complex tool execution.
• Implement caching, model/inference optimization, asynchronous processing, parallel execution, and cost optimization strategies.
• Integrate AI applications with CI/CD, monitoring, logging, tracing, and observability platforms.
• Translate complex business and product requirements into agentic AI solutions with measurable business impact.
• Work closely with product managers, software engineers, data scientists, architects, and business stakeholders.
• Build solutions that move beyond prototypes into scalable, secure, production-ready enterprise applications.

Benefits

• Competitive Salary
• Dynamic Career Growth
• Idea Tanks
• Growth Chats
• Snack Zone
• Recognition & Rewards
• Company-sponsored certifications in AI, Data Science, Cloud, and Analytics technologies

What This Job Offers

• Job Type: Full-time
• Career Level: Senior
• Education Level: No Education Listed