Staff Software Engineer – AI & MCP

RevSpring • Boston, MA

10h

About The Position

Assume a technical leadership role on the team, with ownership of solutions, systems, and projects. Develop, review, test, and debug code to support software products. Contribute to the growth and development of other software engineers and teams. Develop and execute tactical and strategic plans from discovery through delivery. Understand requirements and translate them into high-quality, production-ready deliverables that support progress on the product roadmap and customer commitments.

Requirements

• 7+ years of experience with Java and 4+ years of experience with Python.
• Advanced expertise in Elasticsearch, including cluster architecture, index management, and implementing hybrid search (combining traditional BM25 lexical search with semantic vector/k-NN search and RRF scoring).
• Proven experience designing and orchestrating large-scale ETL pipelines using Apache Beam/Google Cloud Dataflow (Java) , Apache Airflow (Python) , and modern data warehouses like BigQuery.
• Experience building scalable Java and Python microservices, designing high-performance APIs, and developing AI tooling (e.g., Model Context Protocol (MCP) servers, LLM tool/function calling, and prompt orchestration).
• 4+ years of experience using relational databases and deep knowledge of SQL.
• Strong understanding of containerization (Docker) , CI/CD methodologies (e.g., GitHub Actions) , Git , and managing services within cloud platforms (3+ years of GCP experience preferred).
• Ability to read, analyze and interpret general business periodicals, professional journals, technical procedures or governmental regulations.
• Ability to write reports, business correspondence and procedure manuals.
• Ability to effectively present information and respond to questions from a variety of both internal and external sources.

Responsibilities

• Partner with product managers, data engineers, and business leaders to translate complex product requirements into scalable backend solutions, robust AI tooling, and highly relevant search experiences.
• Design, build, and optimize large-scale distributed batch processing pipelines (using Apache Beam/Dataflow and Airflow) to transform high-volume healthcare data into structured search indices and vector embeddings.
• Develop resilient Java and Python microservices, including building Model Context Protocol (MCP) servers, orchestrating LLM function calling, and integrating with external REST/SOAP APIs.
• Deeply optimize Elasticsearch architecture and query latency, implementing advanced hybrid search techniques (combining BM25, semantic vector search, and RRF ranking) to ensure precise relevance and system scalability.
• Write clean, maintainable code and lead by example through rigorous code reviews, architectural design discussions, and mentoring, driving a culture of high-quality software development.
• Stay at the forefront of industry trends in information retrieval, AI orchestration, and modern data engineering, proactively applying these advancements to enhance our platform and AI agents.

What This Job Offers

• Job Type: Full-time
• Career Level: Mid Level
• Education Level: No Education Listed
• Number of Employees: 251-500 employees