Generative AI Developer

Marsh•Jackson, MS

1d•$83,200 - $124,800•Remote

About The Position

Our not-so-secret sauce. Award-winning, inclusive, Top Workplace culture doesn’t happen overnight. It’s a result of hard work by extraordinary people. The industry’s brightest talent drive our efforts to deliver purposeful work and meaningful impact every day. Learn more about what makes us different and how you can make your mark as a Gen AI Developer at MMA. Marsh McLennan Agency (MMA) provides business insurance, employee health & benefits, retirement, and private client insurance solutions to organizations and individuals seeking limitless possibilities. With offices across North America, we combine the personalized service model of a local consultant with the global resources of the world’s leading professional services firm, Marsh (NYSE: MRSH). A day in the life. We are seeking Gen AI Developer who can build, test, and deploy applications powered by large language models and machine learning tools.

Requirements

Designing and delivering AI-enabled applications and agentic systems in production
Building multi-agent architectures, including planner, executor, reviewer, critic, and supervisor patterns
Developing tool-calling, function-calling, and memory-enabled agents
Using LangChain, LangGraph, and similar frameworks for orchestration and workflow design
Applying DSPy, prompt engineering, and optimization techniques to improve quality and repeatability
Building production-grade AI services in Python
Integrating with leading LLM platforms such as Anthropic, OpenAI, and open-source models
Designing RAG solutions using vector databases
Integrating AI systems with enterprise platforms through APIs, workflows, events, and data services
Implementing observability, evaluation, and optimization for AI systems, including tracing, decision logging, and performance monitoring
Working within governance, security, privacy, and compliance frameworks, ideally in regulated industries
Leading complex technical delivery while collaborating effectively across engineering, product, business, risk, and compliance teams
Overall 10+ years of technology experience, including delivery of scalable, resilient digital products

Responsibilities

Review system performance: Check logs for API errors, latency issues, and output quality from deployed models.
Prompt engineering: Refine and test system prompt to improve response accuracy and reduce hallucinations.
Integrate APIs: Connect large language models (like GPT-4 or Claude) with internal databases using retrieval-augmented generation (RAG) frameworks.
Build pipelines: Write Python code to process data, embed documents, and manage vector databases (such as Pinecone or Milvus).
Fine-tune models: Adjust model weights or train smaller open-source models on domain-specific company data.
Collaborate with teams: Meet with product managers and software engineers to align AI features with user needs.
Run evaluations: Test the application for safety, bias, and edge-case failures using automated testing tools.
Optimize costs: Review token usage and API spending to keep cloud infrastructure efficient.
Deploy updates: Push new code updates to production environments using CI/CD pipelines.