Lead Agentic AI Engineer

About the Role

We are seeking a Lead Agentic AI Engineer to architect, develop, and deploy sophisticated AI agents capable of executing intricate, multi-step workflows through natural language interaction. This role entails the integration and orchestration of large language models (LLMs), agent frameworks, Model Context Protocol (MCP) tools, AI coding assistants, context/harness engineering, APIs, and enterprise systems to deliver intelligent assistants that can reason, perform actions, and verify outcomes. Candidates should possess practical experience beyond simple chatbot prototypes, demonstrating solid software engineering capabilities and production-grade AI deployment.

Key Responsibilities

• Develop autonomous and semi-autonomous agents powered by LLMs to handle complex multi-step tasks using frameworks like LangGraph, LangChain, Semantic Kernel, or AutoGen.
• Implement agent orchestration including planning, task breakdown, tool selection, execution monitoring, retry logic, and validation loops.
• Enable agents to interface naturally with enterprise applications, APIs, databases, and developer tools.
• Design and execute context engineering strategies that supply agents with necessary instructions, task contexts, application states, tools, and relevant data at precise times.
• Develop and maintain AI agent harnesses that manage state, permissions, workflow executions, guardrails, retries, and automated verification.
• Engineer repository and application contexts for AI coding agents such as Claude Code and OpenAI Codex, enhancing coding workflows and validation mechanisms.
• Optimize context utilization to minimize token usage, reduce latency, and control LLM costs.
• Design and build MCP servers and tools to facilitate agent interactions with enterprise services including source control, artifact stores, collaboration platforms, databases, APIs, and CI/CD pipelines.
• Establish secure tool invocation with proper authentication, authorization, human approval workflows, and reusable action tools.
• Integrate and orchestrate various LLMs for reasoning, planning, content and code generation, and execution; apply prompt engineering, model routing, fallback, and RAG techniques as necessary.
• Develop evaluation frameworks to assess agent task success, accuracy, response quality, hallucination, reliability, and business impact, including automated and LLM-based judging methods.
• Build regression tests, validation workflows, guardrails, error handling, retry mechanisms, and human-in-the-loop controls for safety and reliability.
• Engineer production-grade AI services leveraging Python and FastAPI or comparable frameworks; deploy and maintain applications on cloud or enterprise infrastructures.
• Design scalable architectures supporting concurrent users, extended workflows, tool executions, caching strategies, and inference optimizations.
• Integrate AI applications with CI/CD pipelines, monitoring, logging, tracing, and observability tools.
• Collaborate with cross-functional teams to translate complex business and product requirements into scalable, secure, enterprise-ready agentic AI solutions with measurable impacts.

Required Qualifications and Skills

• 4 to 10 years of professional experience in AI/ML, generative AI, or software engineering with demonstrated production experience in agentic AI systems.
• Proficiency in Python development including API and AI service creation with frameworks like FastAPI.
• Expertise in context engineering and AI agent harness concepts including agent instructions, context management, permissions, validation, retries, and verification automation.
• Experience working with AI coding agents such as Claude Code or OpenAI Codex, particularly repository context and code workflow automation.
• Hands-on knowledge of MCP development and integrating agents with enterprise tools such as Git, GitHub/GitLab, Artifactory, Slack, databases, APIs, and SaaS platforms.
• Strong command over LLM orchestration, multi-agent workflows, and agent architecture concepts including task planning, tool calling, memory management, and workflow coordination.
• Familiarity with retrieval-augmented generation (RAG), vector embeddings, semantic search techniques, chunking, re-ranking, grounding, and automated LLM evaluation methodologies.
• Solid software engineering background with experience in cloud platforms (AWS, Azure, GCP), containerization (Docker), databases, asynchronous programming, parallel processing, and distributed systems.
• Competence in optimizing LLM usage concerning performance, latency, hallucination mitigation, token usage, caching, and cost control for scalable production AI solutions.

Additional Information

• Competitive Salary: Compensation aligns with your expertise and contributions, recognizing the value you add.
• Career Progression: Access to mentorship, resources, and opportunities that accelerate your professional growth.
• Innovation Environment: Encouragement to engage with new ideas and drive technological advancements.