Description
Title:Senior AI Software Engineer (Agentic AI)
Location: San Francisco, CA
Duration: 3 months
Work Engagement: W2
Work Schedule: Hybrid 3 days in office/2 days remote
Compensation: $90 per hour - $100 per hour is the pay range that the employer reasonably expects to pay for this position
Benefits on offer for this contract position: Health Insurance, Life insurance, 401K and Voluntary Benefits
Summary:
In this contingent resource assignment, you may: Consult on complex initiatives with broad impact and large-scale planning for Specialty Software Engineering. Review and analyze complex multi-faceted, larger scale, or longer-term Specialty Software Engineering challenges that require in-depth evaluation of multiple factors, including intangibles or unprecedented factors. Contribute to the resolution of complex and multi-faceted situations requiring solid understanding of the function, policies, procedures, and compliance requirements that meet deliverables. Strategically collaborate and consult with client personnel. Required Qualifications: Specialty Software Engineering experience, or equivalent demonstrated through one or a combination of the following: work or consulting experience, training, military experience, education.
Key Responsibilities:
Develop Agentic AI Solutions
-
Design, build, and enhance AI agents that automate marketing campaign activities.
-
Create multi-agent workflows where AI agents collaborate to complete business tasks.
-
Implement Agentic AI orchestration patterns and decision-making frameworks.
-
Support production AI agents and develop new agents as the platform scales from 6 to 20+ agents.
Build Backend Services and Microservices
-
Develop and maintain Python-based backend applications.
-
Design scalable microservices architectures.
-
Build fault-tolerant, highly available distributed systems.
-
Create event-driven services that integrate with enterprise platforms.
API Development & Integration
-
Design and develop REST APIs.
-
Integrate AI agents with internal and external systems.
-
Build service-to-service communication layers.
-
Support API performance, reliability, and scalability.
Implement LLM-Based Applications
-
Integrate Large Language Models into business workflows.
-
Develop Retrieval-Augmented Generation (RAG) solutions.
-
Build hybrid RAG and knowledge graph-enhanced AI systems.
-
Implement prompt engineering and prompt orchestration strategies.
-
Configure tool calling and model routing capabilities.
Design Enterprise AI Workflows
-
Architect scalable AI workflows.
-
Design agent orchestration frameworks.
-
Optimize AI systems for:
-
Cost
-
Accuracy
-
Latency
-
Reliability
AI Governance and Responsible AI
-
Implement AI guardrails and controls.
-
Build hallucination detection mechanisms.
-
Apply PII redaction and data protection controls.
-
Maintain audit logging and model monitoring.
-
Support human-in-the-loop validation processes.
Vector Database and Semantic Search Development
-
Design and manage vector database architecture.
-
Build embedding pipelines.
-
Develop semantic retrieval systems.
-
Implement re-ranking strategies to improve AI response quality.
Data Engineering Support
-
Work with Kafka and streaming data pipelines.
-
Process large-scale enterprise data for AI applications.
-
Support real-time data ingestion and retrieval workflows.
Optimize System Performance
-
Profile and tune Python applications.
-
Improve database and query performance.
-
Implement caching strategies.
-
Leverage AsyncIO and multiprocessing for scalability.
-
Monitor system reliability and production health.
Collaborate with Technical Teams
-
Participate in daily standups.
-
Work closely with architects, engineers, and AI specialists.
-
Troubleshoot technical issues and blockers.
-
Contribute to solution design and technical decision-making.
-
Provide production support for deployed AI agents.
Key Requirements:
- Applicants must be authorized to work for ANY employer in the U.S. This position is not eligible for visa sponsorship.
-
Python: 5+ years
-
Microservices: 5+ years
-
API Development/Integration: 5+ years
-
MongoDB: 5+ years
-
Agentic AI: 2+ years preferred
- Strong backend Python developer with experience building and supporting microservices-based applications.
- Experience designing and consuming APIs.
- Familiarity with Large Language Models (LLMs), Agentic AI frameworks, and AI orchestration concepts.
- Experience working with MongoDB and vector databases.
- Financial services experience is not required.