Site Reliability Engineer

13 hours, 9 minutes ago
Full-time
Senior
DevOps and Infrastructure
Binance

Binance

Binance operates as a leading blockchain ecosystem and digital asset exchange, integrating digital technology with financial services to facilitate the trading and management of cryptocurrencies.

Capital Markets
5K-10K
Founded 2017
$10M raised

Description

  • Design and operate adaptive, self-correcting, multi-hop retrieval pipelines and Agentic RAG workflows.
  • Develop capabilities including context management, long-term memory, subagents, multi-agent architectures, self-evolving agents, and real-world task execution.
  • Collaborate with researchers and engineers to implement model-capability-driven innovations.
  • Define benchmarks, datasets, annotation strategies, and evaluation methods for RAG and agent systems.
  • Measure and improve retrieval efficiency, latency, groundedness, and task success rates.
  • Use user feedback and production task data to design experiments and continuously improve agent performance.
  • Prototype and iterate on research ideas through tightly managed experimentation loops.

Requirements

  • 2–8+ years of hands-on production experience with LLM, RAG, and AI agent systems.
  • Experience building end-to-end retrieval pipelines using embedding models such as BGE or OpenAI.
  • Experience with vector stores including Qdrant, Milvus, Pinecone, or Weaviate.
  • Knowledge of hybrid search, reranking, chunking, text cleaning, and multimodal data parsing.
  • Experience implementing Self-RAG, Corrective RAG, adaptive retrieval, multi-hop decomposition, and retrieve-reflect-refine workflows.
  • Experience with agent runtimes or orchestration frameworks such as Pi Agent, AgentScope 2.0, or equivalent, including session recovery, sandbox isolation, middleware, multi-tenant runtimes, and plan/execute loops.
  • Strong understanding of LLM and agent concepts including APIs, KV cache, tool use, reasoning, planning, MCP, memory, subagents, and multi-agent systems.
  • Strong prompt and context engineering skills, independent research ability, and experience translating ideas into prototypes.
  • Power-user experience with coding and general-purpose AI agents, plus strong judgment about model behavior.
  • Proficiency with AI-assisted software development and the ability to work across unfamiliar languages, frameworks, and domains.

Benefits

  • Competitive salary and company benefits.
  • Work-from-home arrangement, subject to business team requirements.
  • Career growth and continuous learning opportunities.
  • Autonomous work on fast-paced, innovative projects.
  • Collaboration with global, multidisciplinary talent in a flat organizational structure.
  • Equal opportunity workplace committed to workforce diversity.

Interested in this position?

Apply directly on the company website

Apply Now

Similar Roles

Site Reliability Engineer - Low-Latency Trading Systems

Ondo Finance 11-50 Diversified Financial Services

Ondo Finance is hiring a remote Site Reliability Engineer to own the reliability, observability, and performance of its 24/7 institutional trading platform across traditional and crypto markets.

AWS CockroachDB Datadog Flux GCP GitOps Go Grafana Kubernetes Linux Pandas PostgreSQL Prometheus Python REST API Rust Secrets Management WebSockets
12 hours, 39 minutes ago

DevOps / SRE / DevSecOps Engineer (AWS) - Latin America, Remote

Bluelight Consulting 11-50 Internet Software & Services

Bluelight is hiring a DevOps/SRE/DevSecOps professional to operate secure, reliable AWS-based systems and support high-quality software delivery for consultancy clients.

AWS CI/CD DevSecOps Docker K6 OpenTelemetry PostgreSQL Secrets Management Terraform
12 hours, 39 minutes ago

DevOps / SRE / DevSecOps Engineer (AWS) - Latin America, Remote

Bluelight Consulting 11-50 Internet Software & Services

Bluelight is seeking a DevOps/SRE professional to support complex, compliance-sensitive client systems by building reliable, secure, and observable AWS infrastructure and delivery processes.

AWS CI/CD DevSecOps Docker K6 OpenTelemetry PostgreSQL Secrets Management Terraform
12 hours, 39 minutes ago

DevOps / SRE / DevSecOps Engineer (AWS) - Latin America, Remote

Bluelight Consulting 11-50 Internet Software & Services

Bluelight is hiring a DevOps/SRE/DevSecOps professional to support complex client systems and deliver secure, reliable, and scalable applications within its growing remote software consultancy.

AWS CI/CD DevSecOps Docker K6 OpenTelemetry PostgreSQL Secrets Management Terraform
12 hours, 54 minutes ago

You're on a roll! Sign up now to keep applying.

Sign Up

Already have an account? Log in

Used by 14,729+ remote workers