Deployment Engineer

We are looking for a Forward Deployed Engineer (FDE) who thrives at the intersection of cutting-edge AI technology and real-world business execution. In this role, you won't just write code in a silo—you will embed directly with client teams, map complex and manual workflows, and engineer autonomous AI-agent solutions to replace them.

You will own the solution lifecycle end-to-end: discovery, architecture, build, deployment, and iteration. Working with minimal direction, you’ll serve as the technical authority who bridge the gap between complex agentic architectures and high-impact business outcomes.

Key Responsibilities

Client Embedding & Workflow Discovery: Partner directly with business stakeholders to break down manual enterprise processes, map complex decision-making steps, and translate them into robust agentic workflows.

Agentic AI Engineering: Design, build, and deploy custom multi-agent systems, function-calling pipelines, RAG implementations, and reusable agent skills.

End-to-End System Ownership: Develop production-ready backend services and integration layers to connect AI agents with core enterprise platforms (e.g., SharePoint, Jira, SAP, email).

Cloud & Infrastructure Management: Package, host, and scale agent workloads using modern cloud architectures (AWS AgentCore, serverless, containerized environments) with automated CI/CD.

Safety & Observability: Implement guardrails, human-in-the-loop checkpoints, and agent evaluation loops to ensure reliability, mitigate hallucinations, and ensure enterprise compliance.

Technical Requirements

Agentic AI & LLMs

Frameworks: Hands-on experience with Strands (primary framework), along with familiarity in LangGraph, CrewAI, or AutoGen.

Agent Core Concepts: Deep understanding of tool use, function calling, streaming, context management, system prompts, and chain-of-thought methodologies.

MCP & Agent Protocols: Proven ability to build/consume Model Context Protocol (MCP) servers, alongside multi-agent coordination (A2A), task delegation, and result aggregation.

RAG Pipelines: Hands-on build experience with vector databases (e.g., Pinecone, pgvector, OpenSearch), chunking strategies, embeddings, and retrieval optimization.

Skill Building & Guardrails: Design reusable skills for agent consumption; implement observability, hallucination mitigation, and human-in-the-loop checkpoints.

Backend Development & Data

Python Mastery: Strong experience with Python 3.10+ using async/await and strict type hinting.

APIs & Web Frameworks: Proficiency with FastAPI (or equivalent), REST API design, and modern auth flows (JWT / OAuth2).

Data Processing: Solid SQL skills (queries, filters, joins) and expertise in unstructured data processing (extracting/classifying data from PDFs, Excel, and legacy enterprise documents).

Infrastructure & DevOps

AWS & Hosting: Experience hosting/operating agent workloads using AWS AgentCore (understanding lifecycle, scaling, and invocation patterns) along with core services (EC2/ECS, Lambda, RDS, S3).

Containers & CI/CD: Docker proficiency and experience setting up GitHub Actions pipelines.

Qualifications & Experience

Software Engineering Track Record: Strong foundation in core software engineering principles and production-grade software development.

Production LLM Experience: At least one production project successfully delivered using LLM agents, skill-building architectures, or RAG pipelines.

End-to-End Ownership: Demonstrated ability to drive projects independently from zero to one with minimal guidance.

Client-Facing Communication: Comfortable interfacing with non-technical business partners—gathering requirements, explaining technical decisions, and presenting live solutions.