Sr. Backend Software Engineer

Conch Technologies•Salt Lake, UT

About The Position

The Senior Backend Software Engineer will design, develop, and maintain banking systems that support high transaction volumes, security, and scalability. The role supports banking products such as payment systems, data and reporting, and customer account management solutions. The engineer will contribute across the software development lifecycle, work continuously with stakeholders, and help build financial products and platform capabilities for American Express. Working as part of a nimble agile team, the engineer will contribute to architecture and workflow implementations while ensuring infrastructure and solutions are scalable, reliable, secure, testable, intuitive, maintainable, and able to meet service-level agreements. The position also designs, builds, and operates generative AI capabilities, including LLM-powered services, RAG systems, and tool-enabled workflows, with attention to security, reliability, and scalability. The engineer participates in design and code reviews and may mentor and coach junior engineers.

Requirements

8–13 years of software development experience.
Bachelor's or master's degree in computer science, computer engineering, or another technical discipline is preferred.
Hands-on, collaborative engineering approach and experience mentoring and coaching junior engineers.
Experience designing and implementing highly scalable, low-latency Java- or Go-based applications.
Hands-on multithreaded programming experience.
Experience building LLM-based applications using at least one major model/provider, including prompt engineering, structured outputs, and tool/function calling.
Experience designing and implementing RAG systems, including document ingestion pipelines, embeddings, vector search, and relevance tuning.
Experience integrating LLM applications with tools and enterprise systems such as APIs, databases, and queues; familiarity with MCP concepts or servers for tool and context access.
Understanding of GenAI security and risk controls, including PII handling, prompt injection, and data leakage, and experience with LLM evaluation or observability.
Knowledge of high-availability techniques, caching, and distributed systems.
Experience profiling and analyzing application performance.
Practical knowledge of distributed technologies and tools, including Java, Spring, REST APIs, JSON, XML, Kafka, JDBC, MongoDB, Postgres, NoSQL databases, Spring Boot, Spring Batch, JUnit, Jenkins, and Gradle or Maven.
Commitment to continuous integration, automated and repeatable testing, and collaborative work environments.
Ability to think abstractly and work through ambiguous or under-defined problems.
Ability and willingness to learn innovative technologies, develop working software quickly, and enable business capabilities through innovation.
Excellent written and verbal communication skills.
Familiarity with CI/CD pipelines and DevOps tools such as Jenkins or GitLab.

Nice To Haves

Experience with in-memory computing solutions.
Experience with streaming solutions, preferably Apache Kafka and Kafka Streams.
Hands-on full-stack software development experience.
Hands-on experience with big data technologies such as Python, Hadoop, and Spark.
Experience with container orchestration tools such as Kubernetes and Docker.
Previous experience with payment systems or real-time transaction platforms.
Leadership experience in a fast-paced development environment.
Experience developing APIs for fintech applications.
Experience with vector databases and search stacks such as OpenSearch/Elasticsearch, pgvector, Pinecone, or Weaviate, and embedding lifecycle management.
Experience building LLM agents with tool/function calling, including workflow orchestration, retries, and safe fallbacks.
Experience creating or operating MCP servers or similar abstractions to expose enterprise data and actions to LLM applications with strong authentication and authorization.
Familiarity with LLM evaluation techniques, including golden datasets, human review workflows, and automated scoring, and safety guardrails for regulated environments.

Responsibilities

Design and contribute to workflow implementations and champion workflow orchestration best practices.
Build software as part of a nimble agile team and contribute to architecture and business outcomes.
Ensure infrastructure is safely extensible, scalable, reliable, and meets SLAs for internal and external users.
Develop solutions that are testable, intuitive, and easy to maintain.
Design, build, and operationalize generative AI capabilities and LLM-powered services with a focus on security, reliability, and scalability.
Implement RAG patterns, including ingestion, chunking, embeddings, vector search, and reranking, to ground LLM outputs in enterprise knowledge.
Develop and integrate LLM tool or function-calling agents to orchestrate workflows across internal APIs and services while enforcing least-privilege access.
Use MCP servers/tools or equivalent patterns to standardize LLM access to data sources and operational tools.
Establish GenAI evaluation, monitoring, and guardrails, including prompting standards, hallucination mitigation, PII controls, red-teaming, and offline/online metrics.
Participate in design and code reviews for key components and cross-enterprise initiatives.
Mentor and coach junior engineers.
Profile and analyze application performance and contribute to continuous integration, automated testing, and collaborative engineering practices.