Blend360 - Forward Deployment Engineer - Agentic AI
Posted Updated
Description
Note : If screened-in, you will be invited for initial rounds on 28th November 2026 (Saturday) in Hyderabad.
About the Role :
Blend's Forward Deployed AI Engineering model places senior, hands-on engineers directly within client environments and alongside client teams, creating accountability from solution design through production deployment. Blend is also investing heavily in agentic AI, including reusable orchestration, evaluation, observability, MCP, and production-ready AI foundations.
We are looking for a Forward Deployment Engineer - Agentic AI to design, build, deploy, and continuously improve production-grade AI agents within enterprise client environments. This role combines AI Engineering, software engineering, context engineering, agent evaluation, and client-facing solution delivery.
Key Responsibilities :
Agentic AI Engineering :
- Design and develop LLM-powered agents using Claude Code, OpenAI Codex, or similar AI coding agents.
- Build autonomous and semi-autonomous agents using frameworks such as LangGraph, LangChain, Google ADK, Semantic Kernel, AutoGen, or equivalent.
- Implement agent planning, task decomposition, tool selection, execution, observation, retry, and validation workflows.
- Build multi-agent systems and integrate agents with enterprise applications, APIs, and databases.
Context Engineering :
- Design and implement context engineering strategies including RAG, memory/state management, and dynamic context retrieval.
- Optimize context to improve agent accuracy, reliability, latency, and cost.
Agent Harness Engineering :
- Design and implement agent harnesses that control state, tool access, permissions, guardrails, and human-in-the-loop workflows.
- Integrate agentic workflows with MCP and other enterprise tool protocols.
Agent Evaluation & Quality :
- Design and implement comprehensive agent evaluation frameworks to measure task completion, accuracy, and reliability.
- Implement LLM-as-a-Judge alongside deterministic validation and establish regression testing.
Production AI Engineering :
- Build production-grade AI services using Python, FastAPI, and modern software engineering practices.
- Deploy AI agents within client cloud and enterprise environments, implementing caching, asynchronous processing, and cost controls.
Forward Deployment & Client Engagement :
- Work directly with client teams to understand business problems and translate them into practical AI solutions.
- Troubleshoot production issues and communicate technical concepts effectively to stakeholders.
Qualifications :
- 6 - 15 years of experience in AI Engineering, Machine Learning, Software Engineering, or Data Science.
- Strong Python development skills with experience building APIs using FastAPI.
- Hands-on experience building LLM-powered agentic applications, multi-step workflows, and state management.
- Experience with orchestration frameworks (LangGraph, LangChain, etc.) and MCP.
- Strong software engineering experience with Git, CI/CD, Docker, SQL, and cloud platforms (GCP/AWS/Snowflake/Databricks).
- Strong client-facing communication skills and ability to deliver measurable business impact.
Skills
Sign in to read and join the discussion.