Senior Backend Engineer II, Data & Agentic Context Platforms
Posted 3
views
Summary
Senior backend engineer on Fetch's Data & Agentic Context Platforms team, designing and operating the APIs, data pipelines, and storage/retrieval systems that serve trusted organizational and user context to AI agents at scale. Work centers on distributed systems, streaming/batch data infrastructure, and vector/search retrieval on AWS.
Meet Fetch Engineering
At Fetch, engineering is driven by curiosity, ownership, and a bias toward action. We operate in complex problem spaces where the right answer is not always clear, and success depends on adaptability, critical thinking, and informed decision-making. Our engineers are comfortable navigating ambiguity, understanding tradeoffs, gathering context, and turning uncertainty into progress while maintaining high technical standards.
Engineers at Fetch take pride in building reliable, scalable systems that serve millions of users. You will contribute directly to the codebase, collaborate closely with cross-functional partners, and help shape best practices that elevate the quality of our work. We foster a culture of mentorship and collaboration, where engineers grow by learning from one another and holding a high bar for quality, reliability, and impact.
About the Role:
Fetch is looking for a Senior Backend Engineer II to build the data and context foundation for our agentic platform. You’ll design and operate the backend services, APIs, data pipelines, and storage systems that make trusted organizational and user context available to agents and product experiences with the appropriate latency, quality, security, and cost.
Working closely with agent, machine learning, data, security, and product teams, you’ll own systems from ingestion and modeling through retrieval and serving. You’ll create reusable platform capabilities that account for context semantics, provenance, freshness, permissions, evaluation, and dependable retrieval.
Role Responsibilities:
- Design, build, and operate scalable backend services and APIs that ingest, transform, retrieve, and serve context to agents and product applications.
- Own batch and real-time data flows, including event ingestion, transformation, indexing, storage, and low-latency serving.
- Develop reusable capabilities for agent context, including connectors, context assembly, memory and state interfaces, metadata and provenance, authorization-aware retrieval, and evaluation signals.
- Define data models, schemas, and contracts, and implement validation, lineage, freshness checks, and observability as upstream systems evolve.
- Select storage and retrieval patterns across operational databases, data warehouses and lakes, search systems, caches, and graph or vector technologies based on access patterns.
- Establish SLIs and SLOs, monitor latency and correctness, plan capacity, manage costs, and design graceful failure and recovery paths.
- Translate ambiguous context needs into durable platform abstractions and lead technical designs through implementation, rollout, measurement, and adoption.
- Improve engineering velocity through well-designed SDKs, tools, documentation, deployment patterns, and paved paths.
- Mentor engineers and raise the bar for backend architecture, data quality, operational excellence, and the responsible use of context.
Minimum Requirements:
- 8+ years of professional software engineering experience, including ownership of production backend or distributed systems at meaningful scale.
- Strong programming skills in at least one modern language, such as Go, Python, Java, or Rust, along with proficiency in SQL and data modeling.
- Experience designing and operating APIs, asynchronous workflows, and data-intensive systems with demanding reliability, scalability, latency, and data-quality requirements.
- Experience with modern data infrastructure, including streaming or messaging systems, batch processing, operational databases, and cloud-based data platforms.
- Sound technical judgment regarding data consistency, schema evolution, privacy and access control, failure handling, performance, and cost.
- Experience with AWS, Infrastructure as Code tools such as Terraform or CloudFormation, CI/CD, and modern software delivery practices.
- Ability to lead ambiguous technical problems from architecture through adoption, delivering incrementally and improving systems based on evidence.
- Strong communication and collaboration skills, including the ability to present technical designs, constructively challenge decisions, align cross-functional partners, and mentor other engineers.
- A bachelor’s or advanced degree in Computer Science, Engineering, Data Science, Mathematics, or a related field—or equivalent practical experience.
Preferred Requirements:
- Experience building production agentic or LLM-powered platforms, including context assembly, memory, retrieval, or evaluation systems.
- Experience with vector databases, graph technologies, search platforms, or hybrid retrieval approaches.
- Experience developing internal platforms, SDKs, or paved paths adopted by multiple engineering teams.
- Familiarity with authorization-aware retrieval and the governance of sensitive data, including provenance, lineage, freshness, and privacy.
This is a full-time role that can be held from one of our US offices or remotely in the United States.
Compensation: At Fetch, we offer competitive compensation packages including base, equity, and benefits to the exceptional folks we hire. The base salary range for this position is $190,409 - $224,011. Discover our benefits and how our employees live rewarded at .