Forward Deployed Engineer
First seen by Alion on Aug 22, 2026.
Experience : 6 to 10 Years
Work Mode : Hybrid 3 days/week WFO
Notice Period : Immediate
Payroll : Haparz
Role Overview :
We are looking for a Forward Deployed Engineer (FDE) who can work at the intersection of Agentic AI engineering and enterprise business execution. You will work directly with client teams to understand complex manual workflows and transform them into production-ready AI-agent solutions.
The role requires strong ownership across discovery, architecture, development, deployment, and continuous improvement, with the ability to independently deliver solutions in a client-facing environment.
Key Responsibilities :
- Partner with business stakeholders to understand manual enterprise processes, decision-making workflows, and automation opportunities.
- Design, build, and deploy multi-agent systems, function-calling workflows, RAG pipelines, and reusable agent skills.
- Develop production-grade backend services and integration layers connecting AI agents with platforms such as SharePoint, Jira, SAP, and enterprise email systems.
- Deploy and operate AI-agent workloads using AWS AgentCore, serverless, and containerized architectures.
- Implement guardrails, human-in-the-loop checkpoints, evaluation mechanisms, and observability to improve agent reliability and reduce hallucinations.
- Own solutions end-to-end from proof of concept through production deployment and iteration.
- Collaborate directly with technical and non-technical stakeholders and present working solutions.
Technical Requirements :
- Strong hands-on experience with Agentic AI and LLM-based applications.
- Strands experience is highly important; familiarity with LangGraph, CrewAI, or AutoGen is desirable.
- Strong understanding of tool use, function calling, streaming, context management, system prompts, and agent orchestration.
- Experience building or consuming MCP servers and implementing multi-agent coordination, including A2A, task delegation, and result aggregation.
- Hands-on experience with RAG, embeddings, chunking strategies, retrieval optimization, and vector databases such as Pinecone, pgvector, or OpenSearch.
- Strong Python 3.10+ development skills, including async programming and type hints.
- Experience with FastAPI, REST API development, JWT/OAuth2 and modern authentication flows.
- Strong SQL knowledge and experience processing unstructured enterprise data from PDFs, Excel, and legacy documents.
- Experience with AWS AgentCore and AWS services such as EC2/ECS, Lambda, RDS, and S3.
- Strong Docker experience and hands-on exposure to GitHub Actions / CI-CD.
What Were Looking For :
- 6 to 10 years of strong software engineering experience with production-grade development practices.
- At least one successfully delivered production LLM/AI-agent or RAG project.
- Demonstrated ability to take projects from 0-to-1 with minimal supervision.
- Strong problem-solving and solution architecture capabilities.
- Excellent client-facing communication skills with the ability to understand business problems and translate them into technical solutions.
- Comfortable working in dynamic environments where requirements evolve through direct client interaction.
Skills
Agentic AI, Forward Deployment Engineering, Artificial Intelligence, LLM, RAG, LangGraph, LangChain, Prompt Engineering, SQL