Senior Software Development Engineer - AI Utility Team

Overview:

The Senior Software Development Engineer - AI Utility Team designs, builds, and operates full-stack applications that integrate advanced AI/ML capabilities. The role focuses on agentic architectures, Large Language Models (LLMs), and Retrieval-Augmented Generation (RAG) to deliver secure, scalable, enterprise solutions. The engineer partners closely with product, data science, and platform teams to deliver AI-powered experiences using Gemini Enterprise and Microsoft Copilot while adhering to responsible AI and regulatory requirements.

Duties and Responsibilities:

• Architect, develop, and maintain full-stack services and UIs that integrate LLMs, agents, and RAG pipelines;
• Design agentic solutions (planning, tool-use, memory) and orchestration for multi-step workflows;
• Operationalize Gemini Enterprise and Microsoft Copilot integrations, including identity, permissions, and governance;
• Implement secure data grounding with vector databases (embeddings, chunking, indexing) and guardrails;
• Build evaluation harnesses for AI quality (precision/recall, hallucination checks, safety filters) and telemetry;
• Own CI/CD for AI-enabled services, including automated tests (unit/integration), canary, and rollbacks;
• Collaborate with product and stakeholders to scope, estimate, and prioritize AI features and platform capabilities;
• Conduct performance tuning and cost optimization for LLM usage (token budgeting, caching, prompt design);
• Document architecture, APIs, prompts, and operational runbooks; train and support partner teams;
• Participate in design/code reviews, retrospectives, and continuous improvement;
• Adhere to HIPAA, security, and responsible AI policies (privacy, explainability, monitoring, incident response);
• Participate in the on-call rotation to support critical issues.

AI/ML & LLM Technical Skills:

• Hands-on with LLM platforms: Gemini Enterprise, Microsoft Copilot; experience with OpenAI or Anthropic a plus;
• Agent frameworks and orchestration (e.g., LangChain/LCEL, Vertex AI Agents, Azure OpenAI orchestration, function/tool calling);
• RAG pipelines (document ingestion, text splitting, embeddings, retrieval strategies such as hybrid/BM25, re-ranking);
• Vector databases (e.g., BigQuery vector, Vertex Matching Engine, Azure Cognitive Search, Pinecone) and metadata schemas;
• Prompt engineering and safety guardrails (system prompts, tool descriptions, content filters, grounding, JSON outputs);
• Evaluation & observability (prompt/unit tests, offline eval sets, A/B, tracing, metrics for accuracy, latency, cost);
• MLOps for LLMs (model/version management, feature stores, secrets, key rotation, quota management).

Core Software Requirements:

• 5+ years software development experience (Python, TypeScript/JavaScript, C# or Java) with strong design/debug skills.
• Full-stack frameworks (e.g., React/Next.js, Angular, .NET, Spring) and REST/GraphQL API development.
• Cloud deployment on AWS, Azure and/or Google Cloud (Functions/App Service/Cloud Run, Kubernetes), IaC (Bicep/Terraform);
• Secure application development (authN/authZ, secrets, encryption, threat modeling) and compliance awareness.
• CI/CD (GitHub Actions/Azure DevOps), automated testing, and monitoring (App Insights/Cloud Logging).

Qualifications:

• BS/BA in Computer Science, Software Engineering, or related field; MS/PhD preferred.
• Experience delivering AI-enabled features in production, at enterprise scale.
• Strong communication and collaboration skills with a growth mindset.
• Certifications a plus: AWS Certified Developer, Google Cloud (Vertex AI/Gemini), Microsoft (Azure AI/AI-900), PMP/CBAP for project leadership.

Physical Demands and Work Environment:

• Sedentary work (sitting for long periods).
• Occasional lifting up to 10 pounds.
• Inside environmental conditions.
• Travel less than 10%, typically for training or collaboration.