Specialty Software Engineer

Location: San Francisco, CA Salary: $80.00 USD Hourly - $86.00 USD Hourly Description:
Senior Backend Engineer, Agentic AI

We are not accepting C2C or 1099 arrangements.

Location: San Francisco, CA
Work Model: Hybrid, approximately 3 days onsite per week
Preferred Onsite Days: Monday, Wednesday, and Thursday, with flexibility
Work Authorization: H-1B candidates may be considered
About the Role

We are seeking a Senior Backend Engineer, Agentic AI to join a highly visible Consumer Technology and Marketing Technology initiative focused on building next-generation Agentic AI solutions.

In this role, you will design, build, enhance, and support AI agents that orchestrate and automate marketing campaign activities. This is a hands-on engineering position with a strong emphasis on coding, backend development, distributed systems, APIs, and Generative AI.

The program is operating in a greenfield environment and is moving from initial development into its next phase of scale and enhancement. The team has already developed six AI agents, with a longer-term roadmap expected to expand to more than 20 agents.

You will work closely with engineers and architects in an agile, collaborative environment while maintaining significant ownership of the solutions you develop.
What You'll Do

• Design, develop, test, deploy, and support production-grade Agentic AI applications and services.
• Build scalable backend services and microservices using Python and FastAPI.
• Design and integrate REST APIs across distributed systems.
• Develop AI agent workflows that use Large Language Models (LLMs), tool calling, orchestration, routing, and fallback strategies.
• Design and implement multi-agent workflows for complex business processes.
• Build Retrieval-Augmented Generation solutions, including RAG, hybrid RAG, and knowledge graph-enhanced RAG architectures.
• Develop embedding, semantic search, retrieval, and re-ranking pipelines.
• Integrate MongoDB, vector databases, and streaming data platforms with AI applications.
• Apply AsyncIO, multiprocessing, caching, profiling, and database optimization techniques to improve application performance.
• Design highly available, fault-tolerant, and event-driven backend systems.
• Implement responsible AI capabilities, including guardrails, PII redaction, audit logging, human-in-the-loop validation, and model monitoring.
• Evaluate LLM performance, including accuracy, latency, cost, hallucination risk, and model quality.
• Develop prompting and orchestration strategies, including schema-aware prompting and Text-to-SQL use cases.
• Troubleshoot technical issues and clearly communicate engineering dependencies and blockers.
• Collaborate closely with developers and architects through daily standups, design discussions, and hands-on development.

Minimum Qualifications

• 5+ years of professional software development experience using Python.
• 5+ years of experience designing or developing microservices-based applications.
• 5+ years of experience developing and integrating APIs.
• 5+ years of experience working with MongoDB or comparable NoSQL database technologies.
• Experience developing scalable backend applications or distributed systems.
• Experience with REST API development and service-oriented architecture.
• Experience with application performance optimization, profiling, caching, or database/query optimization.
• Experience designing production systems for availability, resiliency, and fault tolerance.

Preferred Qualifications

• 2+ years of experience with Agentic AI, Generative AI, or LLM-based application development.
• Experience developing applications using FastAPI, AsyncIO, and multiprocessing.
• Experience designing multi-agent AI systems and agent orchestration workflows.
• Experience with Retrieval-Augmented Generation and advanced retrieval architectures.
• Experience with vector databases, embeddings, semantic search, and re-ranking.
• Experience with prompt engineering and prompt orchestration.
• Experience implementing LLM tool calling, routing, and fallback strategies.
• Experience with LLM and model evaluation frameworks.
• Experience implementing hallucination detection and human-in-the-loop validation.
• Experience with Text-to-SQL and schema-aware prompting.
• Experience developing enterprise AI platforms or scalable AI services.
• Experience implementing AI governance, Responsible AI controls, and AI guardrails.
• Experience with PII redaction, audit logging, and model usage monitoring.
• Experience balancing model accuracy, latency, and cost in production AI systems.
• Experience with AI/ML feature engineering, recommendation systems, or model feedback loops.
• Experience with Kafka and streaming data pipelines.
• Experience with event-driven architectures.

Technical Expertise

The ideal candidate will bring experience across several of the following areas:

Backend Engineering

• Python
• FastAPI
• REST APIs
• Microservices
• Distributed systems
• AsyncIO
• Multiprocessing
• Event-driven architecture
• Performance profiling and tuning
• Caching
• Database and query optimization
• High-availability and fault-tolerant systems

Generative AI & LLMs

• Large Language Models
• Agentic AI
• Multi-agent systems
• RAG and hybrid RAG
• Knowledge graph-enhanced RAG
• Prompt engineering and orchestration
• Tool calling
• LLM routing and fallback strategies
• Model and fine-tuning evaluation
• Hallucination detection
• Human-in-the-loop workflows
• Text-to-SQL
• Embeddings and semantic retrieval

Data & AI Platforms

• MongoDB
• Vector databases
• Semantic search and re-ranking
• Embedding pipelines
• Kafka
• Streaming data pipelines
• AI governance and guardrails
• Responsible AI
• PII redaction
• Audit logging
• Model monitoring

What Makes This Opportunity Unique

This role provides an opportunity to:

• Work directly with cutting-edge Agentic AI and Generative AI technologies.
• Build new AI capabilities in a greenfield development environment.
• Take meaningful technical ownership of production AI solutions.
• Help scale an enterprise Agentic AI platform from its initial agents to a broader ecosystem of AI-driven capabilities.
• Join a collaborative and highly engaged engineering team.
• Work on a strategically important and highly visible technology initiative.
• Be considered for potential extension or conversion opportunities.

Additional Details

This is primarily a hands-on engineering role. Candidates should expect to spend the majority of their time designing, coding, testing, optimizing, and supporting AI and backend services rather than participating in extensive meetings or executive presentations.

Strong technical communication is important, particularly when collaborating with architects and engineers or identifying dependencies and blockers.

Financial services experience is not required.
Key improvements made

• Clarity: Reorganized the posting into responsibilities, minimum qualifications, and preferred qualifications so candidates can quickly determine fit.
• Candidate experience: Replaced the internal term "resources" with engineers/candidates and made the language more candidate-facing.
• Requirements: Separated true minimum requirements from desirable AI expertise to avoid making the role appear unnecessarily restrictive.
• Searchability: Retained high-value keywords such as Python, FastAPI, Agentic AI, LLM, RAG, MongoDB, vector databases, Kafka, and microservices for recruiter and job-board searches.
• Title: Used Senior Backend Engineer, Agentic AI to clearly communicate both the core engineering discipline and the specialization.

Benefits Featured

Medical, Dental , and Vision Insurance is offered to qualified candidates.

Medical, dental, and vision insurance are available to qualified candidates who meet eligibility requirements.
By providing your phone number, you consent to: (1) receive automated text messages and calls from the Judge Group, Inc. and its affiliates (collectively "Judge") to such phone number regarding job opportunities, your job application, and for other related purposes. Message & data rates apply and message frequency may vary. Consistent with Judge's Privacy Policy, information obtained from your consent will not be shared with third parties for marketing/promotional purposes. Reply STOP to opt out of receiving telephone calls and text messages from Judge and HELP for help.
Contact:
This job and many more are available through The Judge Group. Please apply with us today!