AI Agent Engineer

Insight Global is seeking an experienced Agentic AI Engineer to lead the design, development, and deployment of advanced AI solutions leveraging large language models (LLMs), multi-agent systems, and modern GenAI frameworks. This individual will play a key role in architecting scalable AI applications, driving innovation, and partnering with business stakeholders to deliver intelligent automation and decision-support solutions., Architect and implement agentic AI solutions using modern orchestration frameworks such as LangChain, LangGraph, CrewAI, AutoGen, and similar technologies.

Design and develop multi-agent architectures including planner-solver frameworks, hierarchical agents, autonomous agent teams, and goal decomposition workflows.

Define end-to-end GenAI architectures encompassing model selection, orchestration, memory management, tool integrations, observability, security, and deployment strategies.

Build reusable AI tooling, APIs, and memory architectures that support scalable and efficient agent interactions.

Lead development and production deployment of AI-powered assistants, copilots, workflow automation platforms, and decision-support applications.

Evaluate, integrate, and optimize commercial and open-source LLMs, multimodal AI models, and Retrieval-Augmented Generation (RAG) solutions.

Improve system performance, reliability, scalability, and cost efficiency while ensuring adherence to responsible AI, security, privacy, and compliance standards.

Establish GenAIOps and LLMOps best practices, including monitoring, evaluation, logging, testing, and continuous improvement processes.

Mentor engineering teams on agent design patterns, prompt engineering, model optimization, and AI implementation best practices.

Collaborate with product, business, and technical stakeholders to translate requirements into scalable AI solutions and strategic roadmaps.

Stay current with advancements in multi-agent systems, cognitive architectures, and emerging AI technologies

Bachelor’s degree in Computer Science, Engineering, Data Science, Artificial Intelligence, or a related field.

10+ years of overall technology experience, including 5+ years supporting AI engineering platforms in the healthcare, biotechnology

Experience developing domain-specific GenAI solutions within Life Sciences environments.

Strong expertise with agentic AI frameworks including LangChain, LangGraph, CrewAI, AutoGen, Haystack, AutoGPT, BabyAGI, CAMEL, and MetaGPT.

Advanced Python programming skills and experience with prompt engineering, tool integration, agent orchestration, vector databases, RAG pipelines, and memory architectures.

Experience working with leading LLMs such as GPT-4, Claude, Gemini, Mistral, and other commercial or open-source models.

Proven experience designing, deploying, and managing cloud-native AI solutions on AWS, Azure, and/or Google Cloud Platform.

Strong architecture and technical leadership experience with a track record of delivering complex AI initiatives from proof of concept through production deployment.

Experience with model performance optimization, scalability planning, cost management, and operational support of AI systems. Experience with reinforcement learning, agent simulation, or environment modeling.

Knowledge of AI governance, regulatory compliance, privacy requirements, and responsible AI practices within enterprise environments.

Prior experience supporting regulated Life Sciences, pharmaceutical, or biotechnology organizations.