Lead Backend Engineer – Automation & Platform Implementation

Assembly Industries

22h•Remote

About The Position

Assembly Industries is building an AI enabled talent platform that connects top-tier, highly skilled global professionals with innovative companies across the US. As a fast-growing startup, we are laser-focused on impactful growth, agile strategies, and exceptional results. As a Backend Engineer focused on Automation & Platform Implementation, you will split your time between two critical functions: engineering our internal orchestration infrastructure and directly executing customer-facing platform deployments. This isn’t just a "scripts-and-glue" automation role. You will help build and scale a robust orchestration engine utilizing Java microservices and NoSQL document databases that underpins our AI-enabled operations. Concurrently, you will act in a Forward-Deployed Engineering capacity—wiring up integrations, translating complex client workflows, and hardening production deployments. While you aren't expected to be an ML researcher, you must understand how to architect backend systems for semantic search, retrieval pipelines (RAG), and multi-step agentic workflows. If you excel at solving distributed systems problems one day and diving into cross-functional implementation or troubleshooting customer environments the next, this role is for you.

Requirements

4–6 years of software engineering experience building resilient production backend systems and working with distributed architectures.
Strong proficiency in Java, with deep experience developing scalable microservices, handling asynchronous jobs, retries, idempotency, and system failure modes.
Experience with NoSQL document databases (e.g., MongoDB, Firestore, Couchbase) for state and metadata tracking.
Experience building or integrating workflow engines or enterprise automation systems (beyond one-off scripting).
Working knowledge of Python for building integrations, tooling, and rapid prototyping.
Solid understanding of LLM application structures, including embedding systems, vector search, retrieval mechanics, context windows, and agent/tool execution.
Strong interest or hands-on experience in semantic search, RAG pipelines, or conversational AI backends.
High Agency & Independent Execution: You have a strong sense of ownership and the exceptional self-direction required to navigate undocumented paths, make sound architectural calls, and take a project to completion with minimal guidance.
Thrives in a Startup Environment: You are energized by a fast-paced, evolving startup environment, are comfortable when requirements pivot, and are explicitly not looking for a predictable, mature role at a big company.
Wears Multiple Hats Comfortably: You gladly step outside a narrow engineering lane. You can context-switch seamlessly between core backend engineering, customer fire drills, and partner-facing implementation without losing quality.
Customer-Facing Technical Experience: Proven ability to interface with product teams, solution architects, and customer stakeholders to translate vague user requirements into working, deployed software.
Strong Documentation Culture: A consistent habit of writing clear system designs and deployment guides so that the next team member never has to start from zero.

Nice To Haves

Familiarity with durable execution systems or workflow engines (e.g., Temporal, Airflow, Camunda).
Experience designing plugin, connector, or developer framework ecosystems.
Understanding of Edge/serverless computing or Backend-for-Frontend (BFF) patterns for customer-facing apps.
If you've built automation backends, retrieval/search systems, or agent workflows on your own time and can showcase them, that is a massive plus.

Responsibilities

Build, extend, and optimize Java-based microservices responsible for task execution, state management, and orchestration logic.
Model and manage NoSQL document databases to track execution state, workflow metadata, and session/context persistence.
Define internal API contracts, adapters, and connectors that enable modular integration with external APIs and customer deployments.
Implement production-ready infrastructure for data ingestion, document chunking, embedding indexing, and retrieval (RAG) pipelines.
Architect backend services that support multi-step agentic flows, including context assembly, tool calls, and session memory.
Turn product requirements for semantic search and AI assistant features into resilient, production-grade backend code.
Deploy, configure, and customize the automation platform to meet specific customer use cases and business requirements.
Connect external systems through custom sync pipelines, webhooks, and enterprise integrations (e.g., OAuth, ETL-style ingestion).
Debug production issues across our stack and customer environments, capturing field insights to improve the core platform.
Enhance platform observability by setting up robust tracing, execution visibility, and debugging tools for failed runs.