Software Engineer / Subject Matter Expert

We are seeking an experienced Software Engineer / Subject Matter Expert (SME) to join a high-performing Agile development team supporting the design, development, and enhancement of mission-critical software solutions. The successful candidate will have extensive experience developing modern web applications, designing scalable search and retrieval systems, and integrating Artificial Intelligence (AI) and Large Language Model (LLM) technologies into enterprise environments.

This role requires expertise in full-stack software development, cloud technologies, Elasticsearch, Retrieval-Augmented Generation (RAG), and modern DevOps practices within a Lean Agile environment.

Key Responsibilities

• Participate in Agile ceremonies including sprint planning, daily stand-ups, backlog grooming, sprint reviews, and retrospectives.
• Collaborate with product owners, engineers, architects, security teams, operations personnel, and testers throughout the software development lifecycle.
• Design, develop, enhance, and maintain scalable enterprise software applications.
• Translate business, customer, and system requirements into technical designs and software solutions.
• Develop modern Single Page Applications (SPA) using React, HTML5, CSS3, and JavaScript.
• Design and develop RESTful APIs using Node.Js, Express, or comparable backend technologies.
• Build scalable enterprise search and retrieval capabilities utilizing Elasticsearch.
• Design, develop, and integrate AI-powered solutions using Large Language Models (LLMs), including Retrieval-Augmented Generation (RAG) architectures.
• Develop data ingestion, indexing, embedding, and vector search pipelines supporting AI-enabled applications.
• Implement software testing, debugging, code reviews, and quality assurance activities.
• Manage software versioning, vendor software updates, and patch management.
• Support cloud-based deployments and application integration within AWS and/or Microsoft Azure environments.
• Utilize DevOps tools and CI/CD pipelines to automate software delivery and deployment.
• Provide technical support, troubleshooting, and engineering expertise throughout the software lifecycle.

Required Qualifications

Candidates should possess demonstrated experience in the following areas:

Software Development

• Full software development lifecycle (SDLC) within a Lean Agile environment.
• Designing technical solutions based on customer and system requirements.
• Developing enterprise software applications and system interfaces.
• Front-end development using:
  • React (modern Hooks architecture)
  • HTML5
  • CSS3
  • JavaScript
• Back-end development using:
  • Node.Js
  • Express
  • RESTful API development

AI & Search Technologies

• Designing and implementing Large Language Model (LLM) solutions.
• Building Retrieval-Augmented Generation (RAG) applications.
• Developing semantic search and AI-assisted retrieval systems.
• Designing enterprise search architectures using Elasticsearch.
• Creating data ingestion, document chunking, embedding generation, vector search, and retrieval pipelines.
• Experience with search relevance tuning, index optimization, and scalable search architectures.

Cloud & DevOps

• AWS and/or Microsoft Azure cloud environments.
• Git source control.
• Jenkins CI/CD.
• Nexus or similar artifact repositories.
• Software version control and release management.

Web Technologies

• Internet and web technologies including:
  • Node.Js
  • Apache Tomcat
  • Web Services
  • SSL/TLS

Testing

• Unit testing
• Automated testing frameworks such as:
  • Jest
  • Karma

Preferred Qualifications

Preference will be given to candidates with experience in:

• Sponsor-specific Lean Agile development methodologies.
• Evaluating, selecting, and integrating commercial or open-source Large Language Models into enterprise environments.
• OpenAI, Anthropic, or similar LLM platforms.
• Hybrid search architectures combining keyword and semantic search.
• Vector databases and embedding technologies.
• AI relevance optimization and prompt engineering.
• Enterprise search architecture.
• Technical leadership, solution architecture, and mentoring software engineering teams.
• Establishing best practices for AI, enterprise search, and Retrieval-Augmented Generation (RAG).

Ideal Candidate Profile

The ideal candidate will demonstrate:

• Extensive experience designing and deploying production-grade Retrieval-Augmented Generation (RAG) solutions.
• Advanced expertise with Elasticsearch, including:
  • Index architecture
  • Schema design
  • Query optimization
  • Relevance tuning
  • Performance scaling
• Strong understanding of hybrid search methodologies (keyword and vector search).
• Experience building complete AI search pipelines, including:
  • Data ingestion
  • Document preprocessing
  • Chunking
  • Embedding generation
  • Vector indexing
  • Retrieval orchestration
  • LLM integration
• Ability to make software architecture decisions for enterprise AI platforms.
• Experience mentoring engineers and providing technical leadership in AI and enterprise search technologies.

Minimum Acceptable Qualifications

Candidates with the following background will also be considered:

• Experience integrating LLMs, semantic search, or Retrieval-Augmented Generation into enterprise applications.
• Hands-on experience with Elasticsearch or similar enterprise search platforms.
• Strong full-stack development experience using React and Node.Js.
• Experience developing APIs integrating AI or machine learning services.
• Demonstrated ability to quickly learn and adopt emerging AI technologies.

Candidates Who May Not Be a Strong Fit

This position is not intended for candidates whose experience is limited to:

• General full-stack development without meaningful experience in enterprise search or AI-powered retrieval systems.
• Basic chatbot or conversational AI implementations without Retrieval-Augmented Generation (RAG) or semantic search expertise.
• Front-end development without substantial backend API development experience.
• Limited understanding of information retrieval, Elasticsearch, vector search, or Large Language Model integration.
• Inability to explain how enterprise AI systems retrieve, ground, and generate responses using organizational data.