for a long-term, remote contract with our client in the Healthcare industry. Initial contract duration is 6 months, with expected extensions. This can be done 100% remotely from anywhere in the US. Selected individual will be brought in to help develop and deliver
next-generation AI solutions across the healthcare enterprise . This role is hands-on and ideal for an engineer experienced in
building GenAI
and
multi-agent systems
using modern AI frameworks and Google Cloud Platform (GCP). Will collaborate closely with other engineers to design, build, test, and optimize AI capabilities within a scalable production environment.
Want to make an application Make sure your CV is up to date, then read the following job specs carefully before applying.
Key Responsibilities:
Develop and enhance enterprise-scale multi-agent systems leveraging LLMs and autonomous agent frameworks, using tools such as
Google ADK, Agentspace, MCP, RAG,
and
A2A orchestration.
Contribute to the design and implementation of
RAG pipelines
using
BigQuery and Vertex AI
for knowledge grounding and factual response accuracy.
Implement and tune agent reasoning workflows including orchestration, grounding, decision-making, and multi-step reasoning.
Build and support distributed training workflows, online inference systems, and low-latency serving architectures leveraging
Google Cloud services .
Develop secure and scalable AI components including reusable orchestration layers, connectors, and observability hooks.
Participate in developing agent governance and compliance frameworks aligned with enterprise standards.
Translate business features and requirements into technical implementation tasks and contribute to solution design discussions.
Support deployment pipelines, operational monitoring, troubleshooting, and optimization of production AI systems.
Required Qualifications:
Degree in Computer Science, AI/ML, or related technical field.
Hands-on experience in
Generative AI and agentic AI development.
4–5 years of total experience in
AI/ML engineering or applied machine learning.
Experience building and deploying
production AI/ML systems.
Solid understanding of modern model architectures including transformers, embeddings, and prompt engineering concepts.
Hands-on expertise with
Vertex AI
(training, pipelines, deployment, orchestration, and monitoring) and Google Cloud native AI services.
Experience with one or more agent frameworks (i.e.
Google ADK/
Agentspace, LangChain/ LangGraph, LlamaIndex, CrewAI or AutoGen)
Python and LLM integration , including MCP and A2A orchestration.
Experience with
Kubernetes, Cloud Run, Dataflow or Pub/Sub .
Preferred Qualifications:
Experience with AI observability, responsible AI frameworks, and model monitoring tools (Vertex AI Monitoring, BigQuery logging, Looker dashboards).
Experience with multi-modal models and/or advanced optimization strategies.
Contributions to open-source AI tooling or published applied work. xsgimln
Remote working/work at home options are available for this role.