Manager – Forward Deployed Engineer, Agentic AI

About the role

Blend is a premier AI services provider that co-creates measurable business outcomes by moving enterprise AI solutions from experimentation into production. As a Manager – Forward Deployed Engineer, Agentic AI in Hyderabad, TS, India, you will design, build, deploy, and continuously improve production-grade AI agents within enterprise client environments. Day-to-day work combines AI engineering, software engineering, context engineering, agent evaluation, and client-facing solution delivery—translating business problems into agentic architectures, integrating agents with enterprise systems, and owning outcomes from discovery through production deployment and adoption.

What you’ll do

• Design and develop LLM-powered agents using Claude Code, OpenAI Codex, or similar AI coding agents capable of reasoning, planning, using tools, and executing complex multi-step workflows.
• Build autonomous and semi-autonomous agents using frameworks such as LangGraph, LangChain, Google ADK, Semantic Kernel, AutoGen, or equivalent technologies.
• Implement agent planning, task decomposition, tool selection, execution, observation, retry, and validation workflows, including multi-agent systems where specialized agents collaborate.
• Design and implement context engineering strategies and Context APIs, RAG, memory/state management, structured context, and dynamic context retrieval to optimize agent accuracy, reliability, latency,
• Design and implement agent harnesses that control state, tool access, permissions, guardrails, retries, recovery, validation, and execution, including human-in-the-loop workflows and secure tool execu
• Develop and integrate Model Context Protocol (MCP) servers and tools, and connect agents with enterprise systems including databases, APIs, Git/GitHub, Slack, Jira, Artifactory, CRM platforms, and oth
• Design and implement comprehensive agent evaluation frameworks to measure task completion, accuracy, reliability, tool usage, and business outcomes, including evaluation datasets, automated test suite
• Build production-grade AI services using Python, FastAPI, and modern software engineering practices, deploy agents within client cloud and enterprise environments, and integrate with Git, CI/CD, Docke

What you’ll bring

• 6–15 years of experience in AI Engineering, Machine Learning, Software Engineering, Data Science, or a related field, with hands-on experience building and deploying production AI solutions.
• Strong Python development skills with experience building APIs and AI services using FastAPI or similar frameworks.
• Hands-on experience building LLM-powered agentic applications, including multi-step workflows, tool calling, planning, task decomposition, and state management.
• Experience with agent orchestration frameworks such as LangGraph, LangChain, Google ADK, Semantic Kernel, AutoGen, or equivalent.
• Hands-on experience with MCP (Model Context Protocol) and integrating agents with enterprise tools, APIs, databases, and applications.
• Strong experience with context engineering, including context APIs, application state, memory, RAG, dynamic context retrieval, agent instructions, and context optimization.
• Experience with agent harness engineering, including permissions, guardrails, human-in-the-loop controls, retries, recovery, validation, and automated verification.
• Strong software engineering experience with Git, CI/CD, Docker, APIs, SQL/databases, cloud platforms, observability, and production deployment.

Nice to have

• Experience with RAG, embeddings, vector databases, semantic search, reranking, and grounding is highly desirable.
• Experience with Claude Code, OpenAI Codex, or similar AI coding agents, including repository context engineering, agent instructions, automated testing, and verification, is highly desirable.

Skills

Benefits

• Competitive Salary
• Dynamic Career Growth with tools, mentorship, and experiences to accelerate your career
• Company-sponsored certifications in AI, Data Science, Cloud, and Analytics technologies