Lead AI Engineer – Agentic Engineering

This is a fully remote position, open to applicants in India.

📋 Description

• Promote the adoption of Agentic Engineering methodologies throughout the software development lifecycle by utilizing AI agents to enhance and automate engineering workflows.

• Utilize Claude Code, Claude Code Skills, PI, Hermes Agent, and similar AI coding/engineering agents in everyday software development tasks.

• Create AI-supported workflows for requirements analysis, code generation, code comprehension, refactoring, testing, debugging, documentation, code review, and deployment.

• Design agent workflows that comprehend extensive codebases, manage context, utilize tools, perform multi-step engineering tasks, and recover from failures.

• Establish guidelines for context management, context engineering, tool invocation, agent orchestration, guardrails, human-in-the-loop workflows, and autonomous task execution.

• Design and implement assessments to measure agent correctness, reliability, code quality, task completion, regression, and overall effectiveness.

• Analyze emerging agentic coding tools and techniques to enhance engineering productivity and software quality.

• Architect and develop production-quality multi-agent and agentic systems for complex multi-step tasks.

• Design architectures that involve planning, reasoning, tool usage, memory/context management, execution, reflection, validation, and error recovery.

• Integrate agents with APIs, databases, enterprise systems, developer tools, and external services.

• Develop dependable tool-use and MCP-based integrations.

• Build production-grade LLM applications utilizing LangGraph, LangChain, or other comparable orchestration frameworks.

• Implement RAG, semantic search, vector retrieval, structured outputs, and various other LLM application patterns.

• Establish observability, evaluation, monitoring, security, and guardrails for agentic applications.

• Provide technical leadership across AI-driven software products and platforms.

• Apply principles of system design, modular architecture, API design, scalability, reliability, testing, CI/CD, and maintainability.

• Develop production-quality services and APIs using Python, FastAPI, Docker, Kubernetes, and cloud platforms.

• Collaborate with engineering, product, data, and client teams to convert business challenges into scalable technical solutions.

• Conduct technical design reviews and mentor AI/software engineers.

• Establish engineering standards and best practices for AI and agentic applications.

• Lead Agentic AI initiatives and influence architectural and engineering decisions.

• Mentor engineers in AI engineering, agentic architectures, software engineering practices, and AI-assisted development.

• Stay updated on AI coding agents, agent frameworks, LLM capabilities, evaluation methodologies, and engineering practices.

• Prototype new technologies and transition successful methods into robust production solutions.

• Work with clients and internal stakeholders to identify opportunities for measurable Agentic AI value.

• Assist Blend360 in adopting Agentic Engineering throughout the SDLC, enhancing developer productivity, establishing repeatable approaches, safely integrating AI coding agents, improving solution quality/reliability/scalability, and becoming a technical authority.

⛳️ Requirements

• Over 6 years of experience in software engineering or AI engineering.

• Strong hands-on development experience.

• Strong fundamentals in software engineering and experience in developing production-grade applications/services.

• Proven experience in building production-grade Agentic AI systems that exceed basic chatbots or simple RAG applications.

• In-depth understanding of Agentic Evaluation / Agent Evals.

• Experience in creating evaluation datasets, test scenarios, metrics, automated regression tests, and quality gates for agentic applications.

• Ability to assess planning, tool usage, reasoning trajectory, context management, reliability, safety, latency, cost, and task completion.

• Extensive hands-on experience with Python and modern backend/API development.

• Familiarity with LLMs, GenAI, agent orchestration, tool invocation, and RAG.

• Experience with agent frameworks such as LangGraph, LangChain, CrewAI, AutoGen, Google ADK, or similar.

• Comprehensive knowledge of multi-agent architectures, planning, reasoning, context management, tool usage, memory, and agent execution.

• Experience with evaluation frameworks to assess and enhance AI/agent performance.

• Experience with cloud technologies, containers, CI/CD, APIs, databases, and production deployments.

• Solid understanding of software architecture, debugging, testing, scalability, and production engineering practices.

• Practical exposure to utilizing AI agents as engineering tools within the SDLC.

• Experience with Claude Code / Claude Code Skills, PI, Hermes Agent, AI coding agents, or similar agentic development platforms.

• Experience with MCP and developing MCP servers/tools is a plus.

• Familiarity with Claude, GPT, Gemini, Llama, or other advanced models is advantageous.

• Experience with AWS, Azure, or GCP is beneficial.

• Knowledge of Kubernetes, Docker, CI/CD, and cloud-native architectures is a plus.

• Experience with LLM observability and tracing is advantageous.

• Familiarity with Langfuse, Arize Phoenix, OpenTelemetry, or similar technologies is a plus.

• Experience in implementing automated agent evaluations, regression testing, and quality gates is advantageous.

• Experience with distributed systems and scalable AI inference is a plus.

• Experience in consulting or client-facing environments is a plus.

🏝️ Benefits

• Option for remote work.

• Full-time employment.