Backend & AI Engineer (Search + AI Agent Orchestration)

Required Skills

Python
AWS
NLP
Web3
RAG
About micro1
micro1 is a data engine that helps AI labs train foundational models and enterprises build AI agents. We provide frontier evaluations and reinforcement learning environments used to improve LLM capabilities, as well as contextual evaluations used to monitor and improve AI agents in enterprise settings. Our data engine includes an AI recruiter agent that sources and vets domain experts, a data platform that enables rapid production of high-quality training data, and a pipeline performance system that ensures both quality and velocity.
Our goal is to have 1 billion people doing meaningful work by contributing their expertise to the development of frontier AI models. We’ve raised $40M+ in funding, and our AI recruiter has powered more than 1 million AI-led interviews as our global network of experts expands to form the human intelligence layer for AGI.

Job Description

Job Title: Backend & AI Engineer (Search + AI Agent Orchestration)


Job Type: Full-time


Location: Remote


Job Summary

Join our team as a Backend & AI Engineer (Search + AI Agent Orchestration), where you will architect, implement, and maintain the core backend infrastructure for advanced AI-driven search and agent-based systems. You will collaborate across teams to power innovative products leveraging retrieval-augmented generation (RAG), multi-agent orchestration, and cutting-edge NLP in a dynamic and forward-thinking environment.


Key Responsibilities

  • Design, develop, and optimize AI-powered search systems and RAG pipelines across web3 and data-centric products.
  • Build and orchestrate agent-based frameworks for automating complex data retrieval, enrichment, and decision processes.
  • Implement scalable backend systems, APIs, and data pipelines for high-availability, low-latency AI and search experiences.
  • Integrate keyword-based (Elasticsearch, Lucene) and semantic vector search (FAISS, Pinecone, etc.), embedding models, and LLM-powered retrieval in production environments.
  • Develop robust deployment pipelines for web3 AI agents, including on-chain execution of yield strategies.
  • Collaborate with frontend, product, and data teams to ensure alignment between backend features and user needs.
  • Stay ahead of the curve by researching and integrating advancements in RAG, agent orchestration, and NLP technologies.


Required Skills and Qualifications

  • 4+ years’ experience in backend engineering with a strong Python background and production-ready API development.
  • Proven expertise in search systems (Elasticsearch, Lucene) and semantic/vector databases (Pinecone, FAISS, Milvus, etc.).
  • Hands-on experience implementing retrieval-augmented generation (RAG) and working with advanced NLP/LLM models.
  • Proficient with AWS or similar cloud platforms, distributed systems, and high-performance architectures.
  • Strong knowledge of building scalable data pipelines and working with both SQL and NoSQL databases.
  • Experience with AI agent frameworks (e.g., langraph, crewai, autogen) and multi-agent orchestration patterns.
  • Excellent written and verbal communication skills, with a focus on clear articulation and team collaboration.


Preferred Qualifications

  • Experience in web3, blockchain integrations, or deploying AI agents on-chain.
  • Familiarity with monitoring and analytics tools (Prometheus, Grafana, Datadog).
  • Demonstrated ability to work independently while driving alignment with broader team objectives.


What You’ll Gain

Be part of a pioneering journey shaping the future of AI agent orchestration and RAG-based search systems. You’ll collaborate with talented engineers and data scientists, enjoy a highly autonomous and innovative remote environment, and play a vital role in developing impactful, AI-powered products that transform how data is leveraged at scale.

Apply now

Refer and Earn