AI Developer

About the role

Spatial Front, Inc. (SFI) is seeking an AI Developer to support our growing modernization team. The ideal candidate will perform hands-on Python development of artificial intelligence agents and generative AI applications supporting PeopleSoft HCM and related enterprise systems.

Responsibilities

• Design, develop, test, and maintain AI agents and generative AI applications using Python.
• Develop agent workflows that use large language models to interpret user requests, reason across multiple steps, select appropriate tools, retrieve information, and generate grounded responses.
• Develop agent orchestration logic including state management, context management, tool selection, multi-step execution, retries, exception handling, and recovery.
• Develop Python application components using boto3, botocore, and other appropriate SDKs and libraries to interact with AI, data, storage, security, and supporting cloud services.
• Integrate agents with approved tools, APIs, Model Context Protocol (MCP) services, databases, knowledge sources, and enterprise applications.
• Build and optimize retrieval-augmented generation (RAG) capabilities including query formulation, retrieval logic, context assembly, grounding, semantic search, and use of retrieved information within agent workflows.
• Develop prompt and context strategies for working with structured and unstructured enterprise information while minimizing irrelevant or unsupported model responses.
• Create reusable Python libraries, utilities, agent components, prompts, and development patterns that can be used across multiple AI use cases.
• Create automated unit, integration, regression, and AI evaluation tests covering agent workflows, prompts, tool selection, model responses, retrieval quality, and application behavior.
• Analyze model and agent behavior using logs, prompts, responses, tool calls, retrieved context, and downstream results to identify and correct performance or reliability issues.
• Compare and evaluate models, prompting approaches, retrieval strategies, and agent designs based on accuracy, reliability, performance, maintainability, security, and suitability for the use case.
• Collaborate with functional experts and Product Owners to translate business problems into clearly defined AI use cases, expected behaviors, acceptance criteria, and measurable outcomes.
• Support demonstrations, user testing, defect resolution, production validation, monitoring, and continuous improvement of deployed AI capabilities.
• Maintain source code, prompts, technical designs, configuration, evaluation criteria, support documentation, and other AI development artifacts.
• Participate in code reviews, architecture discussions, backlog refinement, demonstrations, testing, release readiness, and other Agile/SAFe delivery activities.
• Other duties as assigned.

Requirements

• Must possess an active Secret security clearance.
• Bachelor's degree in Computer Science, Software Engineering, Artificial Intelligence, Information Systems, Engineering, or a related field; equivalent relevant experience may be considered.
• 3+ years of hands-on software development experience, including strong experience developing production-quality applications and services using Python.
• Strong Python development skills including object-oriented development, modules/packages, dependency management, exception handling, logging, testing, debugging, and API development.
• Hands-on experience developing AI agents, agentic workflows, LLM-based applications, or comparable generative AI capabilities.
• Strong hands-on prompt engineering experience, including development and refinement of system prompts, task instructions, few-shot examples, structured outputs, grounding strategies, tool-use instructions, and context-management approaches.
• Experience developing applications that interact with large language models through APIs or SDKs.
• Experience developing agent workflows that use tools, APIs, or MCP-based services, including tool selection, structured inputs and outputs, error handling, and integration of tool results into agent behavior.
• Experience using boto3 and botocore to develop applications that interact with cloud services and APIs.
• Experience with retrieval-augmented generation (RAG), semantic search, embeddings, vector search, or other knowledge-grounded AI techniques.
• Experience developing REST APIs, consuming APIs, working with JSON, and integrating Python applications with external services.
• Experience developing automated tests or evaluation methods for AI applications, including assessment of response quality, grounding, tool use, or regression behavior.
• Experience with Git/source control, code reviews, CI/CD, debugging, logging, and modern software-development practices.
• Strong troubleshooting skills and ability to diagnose problems across Python code, agent behavior, prompts, model responses, retrieval, tools, APIs, and downstream services.

Desired Skills

• Advanced experience developing agentic AI applications involving multiple tools, multi-step workflows, state management, or complex orchestration.
• Experience designing and optimizing production prompt libraries, agent instructions, reusable prompt templates, and prompt-evaluation approaches.
• Experience evaluating and mitigating hallucination, weak grounding, inconsistent responses, poor tool selection, excessive context, and other common LLM application problems.
• Experience with Amazon Bedrock, foundation-model APIs, or comparable managed generative AI services.
• Experience with agent-development frameworks such as LangGraph, LangChain, Strands Agents, or comparable orchestration technologies.
• Experience building RAG applications using embeddings, vector search, semantic retrieval, hybrid retrieval, document ingestion, or reranking.
• Experience with vector databases or Oracle AI Vector Search is a plus.
• Experience developing AI capabilities involving case management, knowledge management, help desk support, summarization, classification, recommendation, or workflow assistance.
• Experience consuming MCP services and integrating MCP tools into AI agent workflows.
• Understanding of AI application security considerations including prompt injection, inappropriate tool use, excessive agency, sensitive-data exposure, authentication, authorization, and least-privilege access.
• Experience with SQL and relational databases, particularly Oracle.
• Experience integrating AI applications with PeopleSoft HCM, PeopleSoft CRM, or other complex enterprise applications is a plus.
• Experience developing containerized Python applications using Docker and deploying applications into cloud or Kubernetes environments.
• Familiarity with OCI or deployment of AI applications into Oracle Cloud Infrastructure is a plus.
• Experience working in Agile or SAFe environments and using Azure DevOps (ADO) or a similar lifecycle-management tool.
• Experience supporting secured Federal or DoD enterprise systems is preferred.
• Python, AWS, AI/ML, cloud, or related certification is a plus.