Gen AI Engineering Lead

Publicis Groupe•Arlington, VA

About The Position

Publicis Sapient is seeking a highly technical, hands-on Generative AI Engineering Lead to design, develop, and operationalize enterprise Generative AI solutions. The role combines deep Generative AI and LLM engineering expertise with AWS cloud and solution architecture capabilities, alongside formal leadership of approximately 3–5 engineers. The lead will build production-grade solutions involving foundation models, LLMs, AI agents, RAG, MCP, semantic search, APIs, and cloud-native architectures. Working closely with the Enterprise Architect and other stakeholders, the lead will define new solutions, evolve existing architectures, establish reusable engineering patterns, and ensure solutions meet enterprise architecture, security, governance, and operational requirements. The position is hands-on, involving architecture, application design, coding, prototyping, integrations, troubleshooting, code reviews, and technical delivery. The role also champions responsible use of Generative AI to improve engineering productivity and accelerate the software development lifecycle. The successful candidate will deliver secure, scalable, production-ready AI solutions; improve their quality, reliability, observability, and cost effectiveness; develop the engineering team; and establish partnerships across architecture, security, product, and business functions. The position offers a competitive compensation and benefits package. The listed salary range is $155,000–$200,000; actual compensation may vary based on location and required skillset.

Requirements

  • At least 8 years of experience in software engineering, cloud engineering, solution architecture, AI/ML engineering, or related technical roles.
  • Significant hands-on software engineering experience using Python.
  • Strong experience designing and building backend services, REST APIs, microservices, and enterprise integrations using Flask or comparable Python frameworks.
  • Strong hands-on experience designing and developing Generative AI and LLM applications.
  • Demonstrated experience building agentic AI solutions, including tool/function calling, orchestration, state management, memory, and human-in-the-loop workflows.
  • Hands-on experience with LangChain and LangGraph, including stateful agent workflows.
  • Strong experience designing and implementing production-grade RAG solutions.
  • Strong understanding of embeddings, semantic and similarity search, vector databases, metadata filtering, reranking, and hybrid retrieval.
  • Experience implementing or integrating MCP-based solutions or comparable patterns for connecting AI agents to enterprise tools and systems.
  • Hands-on experience with Amazon Bedrock and AWS-based Generative AI solutions.
  • Strong AWS cloud architecture experience, including secure, scalable, resilient, and highly available solutions.
  • Strong understanding of distributed systems, microservices, APIs, and enterprise integration patterns.
  • Experience defining and implementing LLM/RAG evaluation frameworks.
  • Experience troubleshooting and optimizing Generative AI applications across model behavior, retrieval, prompts, latency, reliability, token utilization, and cost.
  • Strong understanding of enterprise AI security, governance, privacy, responsible AI, and production operationalization.
  • Demonstrated ability to translate business requirements into end-to-end solution architectures and technical implementation plans.
  • Experience formally leading or providing technical leadership to engineering teams.
  • Ability and willingness to remain hands-on with architecture, design, coding, prototyping, troubleshooting, and delivery.
  • Excellent communication skills, including explaining complex AI and architecture concepts to technical and non-technical audiences.
  • Ability to understand, evaluate, and communicate emerging Generative AI industry trends and best practices.

Nice To Haves

  • Experience leading teams of 3–5 software, cloud, or AI engineers.
  • Experience building and operating enterprise Generative AI applications in production.
  • Experience implementing multi-agent systems and complex LangGraph workflows.
  • Experience developing MCP servers, MCP clients, or enterprise MCP integration patterns.
  • Experience with multiple commercial and open-source foundation models and evaluating tradeoffs by use case, performance, security, latency, and cost.
  • Experience with vector database technologies and enterprise search platforms.
  • Experience with AWS serverless and container technologies such as Lambda, ECS, EKS, and API Gateway.
  • Experience with Infrastructure as Code, CI/CD, automated testing, and DevSecOps practices.
  • Experience implementing AI observability, tracing, evaluation, and monitoring platforms.
  • Understanding of emerging AI security risks, including prompt injection, data leakage, insecure tool execution, excessive agency, and model misuse.
  • Experience establishing reusable enterprise AI platforms, reference architectures, or engineering frameworks.
  • Experience implementing AI-assisted software engineering practices and measuring effects on developer productivity and software quality.
  • Previous experience delivering technology, cloud, data, or AI solutions for U.S. Federal Government clients.
  • Familiarity with Federal technology environments, security and compliance requirements, governance processes, stakeholder engagement, and delivery in regulated environments.
  • Experience designing or implementing Generative AI, AI/ML, or cloud solutions in a Federal Government environment, including applicable security, privacy, data governance, responsible AI, and authorization requirements.
  • Experience working in a SAFe environment and coordinating across teams, managing dependencies, and supporting planning, backlog refinement, and iterative delivery.
  • Experience partnering with Product Management, Product Owners, Architects, Scrum Masters, and engineering teams to translate architectural initiatives into features and stories in a SAFe delivery model.
  • SAFe, AWS, and/or relevant AI/ML certifications.

Responsibilities

  • Lead the architecture, design, development, and implementation of enterprise Generative AI and LLM-powered applications.
  • Build production-ready solutions using foundation models, prompt engineering, RAG, AI agents, semantic search, and related patterns.
  • Evaluate model capabilities and tradeoffs and recommend suitable models and architectures.
  • Develop reusable AI components, frameworks, patterns, and services.
  • Contribute hands-on to application components, prototypes, integrations, APIs, and reference implementations.
  • Design and implement agentic AI solutions and workflows, including tool and function calling, orchestration, state and memory management, planning, human-in-the-loop processes, multi-agent collaboration, and error recovery.
  • Use LangChain and LangGraph to develop stateful and multi-agent workflows, and establish safe enterprise integration patterns for AI agents.
  • Architect and implement end-to-end RAG solutions, including ingestion, preprocessing, parsing, chunking, embeddings, vector indexing, search, filtering, reranking, context construction, and grounded responses.
  • Optimize retrieval for relevance, groundedness, accuracy, latency, and cost while supporting enterprise data-access controls and security.
  • Design and implement MCP integrations that securely connect AI applications and agents with enterprise tools, APIs, applications, and data sources.
  • Develop authentication, authorization, access-control, and security patterns for AI-driven tool execution and enterprise integrations.
  • Develop Python backend applications and services using Flask or related frameworks, including REST APIs, microservices, AI services, and integration layers.
  • Write production-quality code with appropriate testing, error handling, logging, security, and observability; lead code reviews and establish development standards.
  • Troubleshoot complex application, integration, model, and production issues.
  • Build enterprise Generative AI solutions using Amazon Bedrock and related AWS services, including foundation models, Knowledge Bases, Guardrails, and model APIs.
  • Architect secure, scalable, resilient, highly available cloud-native AI solutions and optimize infrastructure for performance, reliability, scalability, and cost.
  • Translate business requirements into technical solutions and architectures; define system components, interactions, integrations, data flows, security controls, deployments, and technology selections.
  • Partner with the Enterprise Architect on new solutions and enhancements to enterprise architecture; produce architecture diagrams, technical designs, decision records, and implementation guidance.
  • Design distributed applications using microservices and API-based architectures, applying suitable resiliency and event-driven patterns.
  • Establish monitoring and observability practices and operational metrics for production Generative AI applications.
  • Analyze and optimize model performance, prompts, retrieval, token use, latency, reliability, scalability, and infrastructure and inference costs.
  • Ensure AI solutions meet enterprise security, privacy, access-control, governance, responsible AI, monitoring, auditing, and production-readiness requirements.
  • Partner with architecture, security, platform, and governance teams, and mitigate risks such as sensitive-data exposure, prompt injection, and unauthorized tool execution.
  • Lead a team of approximately 3–5 engineers through technical planning, work decomposition, estimation, task assignment, and execution.
  • Provide technical direction, remove blockers, mentor engineers, and conduct design and code reviews.
  • Establish engineering standards, reference architectures, reusable patterns, and practices while balancing delivery and long-term technical sustainability.
  • Promote responsible AI use throughout the SDLC, including requirements analysis, design, development, code review, testing, documentation, troubleshooting, refactoring, and operations.
  • Develop AI-assisted engineering practices with human review, security, and quality controls, and measure and communicate their effects on productivity and software quality.
  • Coordinate across teams and support planning, backlog refinement, dependencies, and iterative delivery in a SAFe environment when applicable.

Benefits

  • Ongoing learning and development opportunities.
  • Competitive compensation and benefits package.
  • Flexibility to support work-life balance.
  • Comprehensive health benefits for the employee and family.
  • Generous paid leave and holidays.
  • Wellness program and employee assistance.
  • Inclusive workplace that promotes diversity and collaboration.
© 2026 Teal Labs, Inc
Privacy PolicyTerms of Service