Software Engineer GEN AI, Assistant Vice President

Description

The company serves clients in more than 160 countries and is investing heavily in enterprise-grade generative and agentic AI that must run securely and reliably inside a tightly regulated financial environment.

You will join the USCC Architecture and AI Engineering team, which runs an enterprise multi-agent AI platform. The platform automates parts of software delivery, from product analysis through to reviewed code that can be deployed.

This is a hands-on individual contributor role as a Generative AI Engineer (AVP), where you will build and scale production parts of the platform. The company wants an engineer with solid computer science, software engineering and applied AI skills who is ready to ship real systems, not only prototypes.

Responsibilities

• Build and run production agents for product analysis, requirements capture, UI prototyping, backlog generation, and automated code changes that open pull requests.
• Create multi-agent workflows in Google's Agent Development Kit (ADK), covering sub-agent orchestration, human approval gates, and agent-to-agent (A2A) messaging.
• Plug Gemini and Anthropic Claude into agent pipelines through enterprise gateways, using prompt engineering and structured tool or function calling.
• Connect agents to engineering and AI product documentation, JIRA and GitHub through MCP-style tool interfaces.
• Build RAG pipelines using vector search, embeddings and clustering so agent answers rest on accurate enterprise context.
• Create evaluation harnesses, including LLM-as-judge and parallel jury methods, to measure faithfulness, relevance, hallucination rate and task completion.
• Write async Python and well-documented FastAPI services backed by persistent PostgreSQL session state.
• Apply data structures, algorithms and complexity analysis to keep orchestration and retrieval efficient at scale.
• Add observability, maintain CI/CD and containerised deployments, apply secure coding and guardrails, and test every change at unit, integration and end-to-end levels.
• Lead the design and delivery of custom AI platform components, including Python, Java (Spring Boot) and React microservices and full-stack apps for LLM/SLM fine-tuning control planes, inference gateways and experiment tracking dashboards.
• Build and tune multi-tenant agents using ReAct and ReWOO patterns with ADK, LangGraph and LangChain.
• Enforce decoupled integration layers using clean architecture, domain-driven design, SOLID principles, and patterns such as Strategy, Factory, Adapter, Circuit Breaker and Saga.
• Write concurrent and async code (asyncio, multithreading, CompletableFuture, virtual threads, connection pooling) for streaming tokens, parallel tool execution and high-concurrency inference.
• Design for high availability, fault tolerance and graceful degradation, using rate limiting, token buckets, exponential backoff retries and Redis caching.
• Design versioned, idempotent REST APIs, gRPC endpoints and WebSockets for streamed LLM output, following OpenAPI and Swagger specifications.
• Build ingestion and retrieval for GraphRAG, LightRAG and RAPTOR, and integrate Neo4j and vector stores (pgvector, Pinecone, Milvus) for semantic, hybrid and relational queries.
• Write deterministic system instructions, classifiers and semantic routing trees that prevent intent collisions and hallucinations in multi-step workflows.
• Work as a Forward Deployed Engineer with subject matter experts to turn business and domain logic into automated, production-ready agent software.
• Work with UI engineers and core API platform teams to connect agent logic to React applications and enterprise service layers.
• Explain complex technical concepts clearly and solve analytical problems.

Requirements

• Strong computer science fundamentals: data structures, algorithms and complexity, operating systems, networking, and relational database design and optimisation.
• Advanced Python, including async, typing and dependency management, plus solid engineering practice in clean code, automated testing, version control and CI/CD.
• Hands-on LLM application development with prompt engineering, tool or function calling, structured outputs, and multi-agent or agentic frameworks.
• Practical RAG pipeline experience with vector databases and embedding-based retrieval, and familiarity with evaluating structured LLM or agent outputs.
• Experience connecting AI systems to external tools and documentation through structured interfaces such as MCP, with working knowledge of Docker and Kubernetes or OpenShift.
• Bachelor's or Master's degree in Computer Science, Software Engineering or a related technical field.
• 4-7 years of professional software engineering experience building scalable backend or full-stack distributed systems.
• 3+ years of AI/ML experience, including at least 2+ years in Generative AI (LLMs, RAG, agentic workflows, MCP).
• Strong grasp of trees, graphs, hash maps, queues and heaps, plus Big-O analysis of time and space.
• Good command of SOLID, clean code, design patterns, separation of concerns and dependency injection.
• Understanding of CAP theorem, event-driven architecture, asynchronous messaging (Kafka or RabbitMQ), idempotency, distributed transactions and database isolation levels.
• Comprehensive testing: unit tests (pytest, unittest, JUnit, Mockito), integration, contract and end-to-end tests, mocking, TDD principles, and LLM evaluation and regression testing.
• Proficiency with Git workflows, automated CI/CD pipelines, Docker, Kubernetes or OpenShift, and infrastructure as code.
• Hands-on use of OpenTelemetry, Prometheus, Grafana and ELK or Loki for distributed tracing, structured logging and metrics, including LLM token latency and tool calls.
• Understanding of OWASP Top 10 and OWASP Top 10 for LLMs, secure authentication and authorisation (OAuth2, OIDC, mTLS, RBAC), secrets management, and data sanitisation and PII redaction.
• Advanced Python, prompt engineering, Google ADK, LangChain, LangGraph and custom state machines.
• In-depth implementation knowledge of Model Context Protocol (MCP) clients and servers.
• Working knowledge of GraphRAG, LightRAG, RAPTOR, hybrid search (BM25 with dense embeddings), cross-encoder re-ranking and chunking strategies.
• Backend experience with FastAPI, Flask, Django, Spring Boot or Spring Cloud; modern React, TypeScript or JavaScript, and responsive UI design.
• Data skills with Oracle or PostgreSQL (schema design, indexing, query tuning, connection management), Neo4j Cypher, pgvector, Pinecone, Milvus, Redis and Apache Kafka.
• Beneficial: direct experience with Google ADK or comparable orchestration frameworks, and observability tools such as Langfuse, Prometheus or distributed tracing.
• Beneficial: exposure to Go, and front-end work with React and TypeScript, including SSE streaming.
• Beneficial: experience with ChromaDB or pgvector, HDBSCAN clustering, HashiCorp Vault, and SSO or JWT authentication patterns.
• Beneficial: experience with GitHub, JIRA, and documentation-search integrations for backlog and pull request workflows.

Conditions

Full-time role based in Irving, Texas, United States.

Salary range is $107,120.00 - $160,680.00.

Applications close on Oct 21, 2026.

Hiring decisions are made by people, and automated processing is not used for autonomous decisions.

Equal opportunity and Illinois AI notice information is provided by the company.

Benefits

• Possible incentive and retention awards for eligible employees.
• Medical, dental and vision coverage, a 401(k), life, accident and disability insurance, and wellness programs.
• Paid vacation, sick leave and holidays.
• Full benefit details are on the company's benefits website, and offerings may vary by jurisdiction, job level and date of hire.