Senior AI Engineer

AllianceBernstein LP•Nashville, TN

12d•Onsite

About The Position

We are building a next-generation enterprise AI and data platform that enables teams to design, deploy, integrate, and scale intelligent applications and agents across investment research, portfolio management, risk, client, and operational workflows. The platform provides standardized infrastructure, reliable data products, commercial and self-hosted model access, retrieval, agent orchestration, evaluation, observability, security, and governance. It enables teams to rapidly deliver AI-powered capabilities in a scalable, secure, and production-ready manner.

Requirements

5+ years of experience in software, data, AI, or platform engineering.
Strong production development experience with Python and SQL.
Proven ability to build and operate AI applications, data pipelines, APIs, data products, and distributed systems.
Experience integrating AI capabilities into enterprise applications and business workflows.
Strong understanding of: Object-oriented and asynchronous Python APIs, microservices, and application integration
Strong understanding of: Data modeling, contracts, quality, reconciliation, metadata, and lineage
Strong understanding of: Batch, streaming, event-driven, and API-based architectures
Strong understanding of: Workflow orchestration, distributed processing, and production operations
Experience with cloud data and AI platforms such as Azure, AWS, Google Cloud, Snowflake.
Ability to design scalable, reusable, resilient, and operationally supportable services.
Hands-on experience with: Large language models, embeddings, prompt engineering, context engineering, and RAG architecture.
Hands-on experience with: Commercial and open-source model APIs and ecosystems.
Hands-on experience with: AI agents, agentic workflows, reusable skills, tool calling, structured outputs, and multi-step orchestration.
Hands-on experience with: Vector, keyword, metadata-filtered, graph-based, and hybrid retrieval.
Hands-on experience with: Agent frameworks such as LangGraph, Microsoft Agent Framework, Semantic Kernel, AutoGen, Pydantic AI, or equivalent platforms.
Experience with one or more of the following: Azure OpenAI, OpenAI APIs, Anthropic Claude, Google Gemini, or Vertex AI.
Experience with one or more of the following: Hugging Face, vLLM, Ollama, Qwen, or other approved open-source model technologies.
Experience with containerized model deployment and GPU-based inference.
Experience with model serving, API gateways, quantization, memory optimization, and model configuration.
Experience with context-window, token, concurrency, batching, throughput, and caching optimization.
Experience with benchmarking and monitoring model quality, latency, availability, resource utilization, and cost.
Strong experience with: CI/CD, infrastructure as code, automated provisioning, and governed deployment.
Strong experience with: API-first and microservices architectures.
Strong experience with: Docker, Kubernetes, AKS, GKE, or equivalent container platforms.
Strong experience with: Authentication, authorization, secrets management, OAuth, managed identities, RBAC, and Microsoft Entra ID or equivalent technologies.
Strong experience with: Repository governance, branch protection, pull-request validation, dependency controls, and software supply-chain security.
Strong experience with: Metrics, distributed tracing, structured logging, monitoring, and alerting.
Strong experience with: Designing observable, resilient, secure, and production-ready AI systems.
Experience using AI-assisted development tools such as Claude Code, GitHub Copilot, Cursor, Codex, or comparable tools for: Code generation, refactoring, debugging, testing, and documentation.
Experience using AI-assisted development tools such as Claude Code, GitHub Copilot, Cursor, Codex, or comparable tools for: Data-pipeline, infrastructure, and CI/CD development.
Experience using AI-assisted development tools such as Claude Code, GitHub Copilot, Cursor, Codex, or comparable tools for: Codebase understanding, modernization, architecture extraction, and pull-request review.
Experience using AI-assisted development tools such as Claude Code, GitHub Copilot, Cursor, Codex, or comparable tools for: Governed development supported by automated testing, peer review, security scanning, and controlled deployment.
Candidates must be able to independently validate AI-generated code for: Functional correctness and test coverage
Candidates must be able to independently validate AI-generated code for: Security and data-access risks
Candidates must be able to independently validate AI-generated code for: Performance and scalability
Candidates must be able to independently validate AI-generated code for: Maintainability and architectural alignment
Candidates must be able to independently validate AI-generated code for: Dependency, licensing, and software supply-chain concerns
Candidates must be able to independently validate AI-generated code for: Compliance with enterprise engineering standards
Required Hands-on experience with data-quality, model-evaluation, LLM-evaluation, or AI-observability frameworks.
Experience building: Model benchmarking and evaluation pipelines
Experience building: Data-quality and reconciliation tests
Experience building: Retrieval and RAG evaluations
Experience building: Agent test harnesses and scenario-based simulations
Experience building: Continuous validation and regression testing
Experience building: Production monitoring for data, retrieval, model, and agent quality
Ability to measure: Data accuracy, completeness, freshness, and consistency
Ability to measure: Retrieval relevance and coverage
Ability to measure: Groundedness, factual consistency, citations, and provenance
Ability to measure: Tool selection, execution, and structured-output compliance
Ability to measure: Agent workflow success, failure, and escalation behavior
Ability to measure: Latency, throughput, reliability, resource utilization, and cost
Familiarity with OpenTelemetry, OpenInference, Datadog, Arize, LangSmith, MLflow, Microsoft Foundry evaluation capabilities, or equivalent tools.
Ability to use evaluation results to inform model selection, routing, release, rollback, and production-readiness decisions.

Nice To Haves

MCP servers and clients, agent-to-agent communication, and enterprise search.
Semantic layers, ontologies, and knowledge graphs.
Agent memory, state management, and human-in-the-loop controls.
Document intelligence and multimodal processing.
Reusable agent tools, skills, manifests, and registration standards.

Responsibilities

Build reliable, reusable, and AI-ready data products for investment and enterprise use cases.
Design and develop production-grade AI applications, agents, and intelligent workflows using Python.
Implement agent orchestration, tool integration, retrieval, memory, and multi-step workflows.
Integrate AI capabilities into enterprise applications, data platforms, and business systems.
Contribute to the shared AI and data platform that powers these capabilities at scale.