Description

You will lead the design, build, and optimization of LLM-based autonomous agents for reasoning, planning, and task execution on Google Cloud Platform.

This role is remote.

Responsibilities

• Develop and deploy machine learning models, including supervised, unsupervised, and deep learning approaches.
• Design secure, scalable GCP cloud architectures using GKE, Compute Engine, Cloud Run, BigQuery, and Cloud Storage.
• Implement Infrastructure-as-Code with Terraform and manage CI/CD pipelines via Cloud Build, Jenkins, or GitHub Actions.
• Integrate with data engineers and scientists to build end-to-end AI agentic solutions for business workflow automation.
• Automate provisioning, scaling, and operational processes while enforcing enterprise guardrails and Responsible AI principles.

Required Skills

• 8+ years of experience in Python development.
• Hands-on expertise with FastAPI or Flask.
• Deep knowledge of LLMs (OpenAI, Gemini, Claude, Llama, Mistral) and agent frameworks (LangChain, AutoGen, CrewAI).
• Proficiency in implementing RAG, semantic search, and vector databases (FAISS, Pinecone, Chroma, Weaviate).
• Strong operational experience with GCP services, specifically Vertex AI, GKE, and VPC networking.
• Ability to implement multi-agent orchestration and generative reasoning optimization (chain of thought, tree of thought, RAP).
• Proficiency in Terraform, Kubernetes, Docker, and shell scripting.
• Understanding of security (IAM, KMS) and SRE concepts (SLIs/SLOs, monitoring).

Preferred Skills

• Experience with workflow tools like Airflow or Prefect.
• Familiarity with enterprise guardrails and Responsible AI frameworks.

Key Skills

Education

Any Graduate