Lead / Manager - Agentic AI Engineer (Claude Code or Codex)

Blend; Hyderabad; On-site; INR 3,000,000 - 6,000,000; Full time

Benefits offered by this job

Competitive salary

Career growth

Idea Tanks

Growth chats

Snack zone

Recognition & rewards

Certifications

Job summary

Blend seeks a Lead/Manager - Agentic AI Engineer to design, build, and deploy production-grade AI agents capable of multi-step workflows via natural language.

The role focuses on integrating LLMs, agent orchestration frameworks, MCP tools, and enterprise systems to create intelligent assistants that reason, use tools, execute actions, and verify results.

Qualifications

• 4–10 years of experience in AI/ML or software engineering, with hands-on production-grade AI applications and agentic systems.
• Hands-on experience with AI coding agents (e.g., Claude Code, OpenAI Codex) and MCP.
• Strong development skills in Python and building APIs, and experience with AI services using FAST API or similar frameworks.

Responsibilities

• Agentic AI Development & Orchestration: design and develop autonomous agents capable of multi-step workflows.
• Context & Harness Engineering: build context strategies and AI agent harnesses to manage state, tools, and verification.
• MCP & Tool Integration: design MCP servers, integrate with enterprise tools, APIs, databases, and CI/CD platforms.
• Production Engineering & Deployment: develop production-grade AI services in Python/FastAPI and deploy in cloud environments.
• Enterprise AI Solutions: translate business requirements into scalable, secure enterprise AI solutions.

Skills

Python

API development

AI services

LangGraph

LangChain

Semantic Kernel

AutoGen

MCP

Git

CI/CD

Education

Bachelor’s degree in CS/related field

Tools

GitHub/GitLab

Artifactory

Database access

Job description

Blend is a premier AI services provider, committed to co-creating meaningful impact for its clients through the power of data science, AI, technology, and people. With a mission to fuel bold visions, Blend tackles significant challenges by seamlessly aligning human expertise with artificial intelligence. The company is dedicated to unlocking value and fostering innovation for its clients by harnessing world-class people and data-driven strategy. We believe that the power of people and AI can have a meaningful impact on your world, creating more fulfilling work and projects for our people and clients. For more information, visit www.blend360.com.

About the Role:

We are looking for an Lead / Manager - Agentic AI Engineer to design, build, and deploy production-grade AI agents capable of executing complex, multi-step workflows through natural language interactions.

The role will focus on integrating LLMs, agent orchestration frameworks, MCP tools, AI coding agents, context/harness engineering, APIs, and enterprise systems to build intelligent assistants that can reason, use tools, execute actions, and validate results.

The ideal candidate has hands-on experience building agentic workflows beyond simple chatbots or PoCs, with strong software engineering skills and experience taking AI solutions into production.

Key Responsibilities:

1. Agentic AI Development & Orchestration

• 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.

2. Context & Harness Engineering

• Design and implement context engineering strategies to 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.

3. MCP & Tool Integration

• Design and develop Model Context Protocol (MCP) servers and tools to 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 allow 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.

5. Agent Evaluation & Reliability

• 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 agent 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.

6. Production Engineering & Deployment

• 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 supporting 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.

7. Enterprise AI Solutions

• 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.

Skills Required:

• 4–10 years of experience in AI/ML, Generative AI, or software engineering, with hands-on experience building production-grade AI applications and agentic systems.
• Strong development skills in Python and building APIs and AI services using FAST API or similar framework along with 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, code workflows, and verification.
• Hands‑on experience with 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.
• 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, and 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, monitoring, and building secure, scalable AI solutions with measurable business impact beyond POCs

Additional Information:

Thrive & Grow with Us

• Competitive Salary: Your skills and contributions are highly valued here, and we make sure your salary reflects that, rewarding you fairly for the knowledge and experience you bring to the table.
• Dynamic Career Growth: Our vibrant environment offers you the opportunity to grow rapidly, providing the right tools, mentorship, and experiences to fast-track your career.
• Idea Tanks: Innovation lives here. Our "Idea Tanks" are your playground to pitch, experiment, and collaborate on ideas that can shape the future.
• Growth Chats: Dive into our casual "Growth Chats" where you can learn from the best—whether it's over lunch or during a laid‑back session with peers, it's the perfect space to grow your skills.
• Snack Zone: Stay fuelled and inspired! In our Snack Zone, you'll find a variety of snacks to keep your energy high and ideas flowing.
• Recognition & Rewards: We believe great work deserves to be recognized. Expect regular Hive-Fives, shoutouts, and the chance to see your ideas come to life as part of our reward program.
• Fuel Your Growth Journey with Certifications: We're all about your growth! Enhance your expertise with company-sponsored certifications in AI, Data Science, Cloud, and Analytics technologies.