This role is central to building next-generation AI systems that operate autonomously and collaboratively through multi-agent architectures. You will design, implement, and maintain intelligent software agents that leverage large language models, retrieval-augmented generation, and secure tool integrations to solve complex business problems. Working closely with cross-functional teams, you will ensure these systems are robust, scalable, and aligned with enterprise security and compliance standards. Your work will directly impact the reliability, efficiency, and intelligence of AI-driven workflows across critical platforms.
Responsibilities
- Create and maintain production-ready Agentic AI systems leveraging large language models, multi-agent coordination, and retrieval-augmented generation pipelines.
- Optimize and refine prompt engineering techniques, including structured prompting, tool usage, and agent orchestration for consistent and predictable AI outputs.
- Develop secure backend services and RESTful APIs in Python to connect AI agents with enterprise platforms using microservices architecture.
- Implement safety measures such as output validation, fallback mechanisms, rate limiting, secure tool access, and human-in-the-loop workflows.
- Build and manage evaluation frameworks for AI models, including automated testing of prompts, retrieval accuracy, regression checks, and performance benchmarks.
- Deploy and maintain AI services on AWS using EC2, S3, Lambda, RDS, and container technologies like Docker and Kubernetes.
- Ensure high system reliability through monitoring, observability, and proactive maintenance of AI-driven applications in production environments.
Requirements
- 3 to 6 years of professional experience in backend or distributed systems development.
- Proficiency in Python and building RESTful APIs.
- Hands-on experience developing applications with large language models, including RAG, embeddings, and vector database integrations.
- Practical knowledge of prompt engineering and understanding of LLM capabilities, constraints, and optimization strategies.
- Proven experience deploying and managing applications in AWS cloud environments.
Nice to Have
- Experience with frameworks for orchestrating multiple AI agents or integrating AI tools.
- Knowledge of vector databases such as Pinecone, Weaviate, or OpenSearch.
- Familiarity with CI/CD pipelines and deploying containerized applications using Docker and Kubernetes.
- Experience connecting AI systems with enterprise platforms like ServiceNow or Snowflake.
- Exposure to observability platforms such as Datadog or Prometheus.
Tech Stack
Large language models (LLMs), Retrieval-augmented generation (RAG) pipelines, Multi-agent workflows, Prompt engineering, Python programming, REST APIs, Microservices architecture, Amazon Web Services (AWS), EC2, S3, Lambda, RDS, Docker, Kubernetes, Vector databases, AI guardrails, Model evaluation frameworks, Security best practices, Observability tools
Benefits
- Flexible time off policy
- Access to wellness resources
- Company-organized team events
- Recognized as a Fortune Best Workplace in Technology™
- Recognized as a Fortune Best Workplace in the Bay Area™
- Certified Great Place to Work®
Compensation
The annual base salary range is $149,000 - $224,000 USD. This role may be eligible for equity and incentive pay.
Work Arrangement
Primarily onsite in Santa Clara, CA; expected to work from the office unless on approved leave, PTO, or business travel.
- We value critical thinking, embrace challenges, and encourage innovation.
- We support personal and professional growth and meaningful contributions.
- We foster collaboration, mutual support, and collective success.
- We are committed to building an inclusive future where every voice is heard.
- We celebrate individuality and actively embrace differences.
Additional Information
- Candidates with disabilities may request reasonable accommodations during the application or interview process.
- This position requires on-site collaboration and is not eligible for remote work.
- Background checks are required for this role due to customer security requirements.
- We are an equal opportunity employer and welcome diverse applicants from all backgrounds.
