Hi,

Greetings from Conch Technologies Inc

Position: Senior Java Engineer -Digital Banking

Location: Salt Lake City, UT

Duration: 12+ Months Contract

Responsibilities:

Design and contribute to workflow implementations
Champion workflow orchestration best practices
Build software as part of a nimble agile Team where you have every opportunity to make an impact on the bottom line and contribute to the architecture.
Ensure our infrastructure is safely extensible, scalable, reliable, and meets SLAs for both external and internal users.
Ensure our solutions are testable, intuitive, and easy to maintain.
Use state-of-the-art tools for remote collaboration and developer happiness, i.e., IntelliJ CodeWithMe and Tuple
Design, build, and operationalize Generative AI capabilities (LLM-powered services) with a strong focus on security, reliability, and scalability.
Implement Retrieval-Augmented Generation (RAG) patterns (ingestion, chunking, embeddings, vector search, reranking) to ground LLM outputs in enterprise knowledge.
Develop and integrate LLM tool/function-calling ("agents") to orchestrate workflows across internal APIs and services while enforcing least-privilege access.
Leverage Model Context Protocol (MCP) servers/tools (or equivalent patterns) to standardize how LLM applications access data sources and operational tools.
Establish evaluation, monitoring, and guardrails for GenAI (prompting standards, hallucination mitigation, PII controls, red-teaming, offline/online metrics).
Participate in design and code reviews for key components and cross-enterprise initiatives.

Qualifications:

8-13 years of software development experience, and preferably a Bachelor's or master's degree in computer science, computer engineering, or other technical discipline.
Team player and a hands-on engineer.
Experience mentoring and coaching junior engineers.
Experience in designing and implementing highly scalable, low latency Java / Go based applications.
Hands-on experience in multi-threading programming.
Hands-on experience building LLM-based applications using at least one major model/provider, and applying 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 (APIs, databases, queues) and familiarity with MCP concepts/servers for tool and context access.
Understanding of GenAI security and risk controls (PII handling, prompt injection, data leakage), and experience with evaluation/observability of LLM systems.
Basic high availability techniques and implementation knowledge.
Practical knowledge of caching and distributed systems.
Staying in touch with industry standards and current technologies is expected.
Experience in profiling/performance analysis of applications.
Core competencies in distributed technologies including Java, Spring, APIs (REST), JSON, XML, Kafka, JDBC, MongoDB, Postgres, NoSQL databases, Spring Boot, Spring Batch, JUnit, Jenkins, and Gradle/Maven.
Experience with In-memory computing solutions is a big plus.
Commitment to software practices of continuous Integration, automated/repeatable testing, and collaborative work environments.
Ability to think abstractly and deal with ambiguous/under-defined problems.
Ability to enable business capabilities through innovation.
Demonstrated willingness to learn innovative technologies and take pride in how fast they develop working software.
Experience working with streaming solutions is highly desirable (preferably Apache Kafka and Kafka Streams).
Hands-on experience in full-stack software development is desirable.
Hands-on experience in Big Data technologies including Python, Hadoop, and Spark is a plus
Have excellent written and verbal communication skills.
Familiarity with CI/CD pipelines and DevOps tools (Jenkins, GitLab).

Preferred Qualifications:

• Experience with container orchestration tools like Kubernetes and Docker.

• Previous experience with payment systems or real-time transaction platforms.
• Leadership experience in a fast-paced development environment.
• Experience in API development for fintech applications.
• Experience with vector databases and search stacks (e.g., OpenSearch/Elasticsearch, pgvector, Pinecone, Weaviate) and embedding lifecycle management.
• Experience building LLM agents with tool/function calling, including workflow orchestration, retries, and safe fallbacks.
• Experience creating/operating MCP servers (or similar abstractions) to expose enterprise data and actions to LLM applications with strong authentication/authorization.
• Familiarity with LLM evaluation techniques (golden datasets, human review workflows, automated scoring) and safety guardrails for regulated environments.

With Regards,
Teja Kumar P
Desk: 380-999-9014
Email: [email protected]
Web: www.conchtech.com