AI Software Engineering Lead - Agentic SDLC (Java)
You have spoken with an Anthology recruiter about this position. Fill in your details, review the agreement, and select “I agree” so we can represent you. Read the job description below, then complete the three steps. It takes about three minutes, and we never submit your profile to a client without your OK.
Job description
W-2 ONLY: Direct W-2 employment with Anthology Solutions Inc. No C2C, 1099, or employment through another staffing supplier. Anthology Solutions Inc. is seeking an experienced AI Software Engineering Lead with a strong Java background to design and implement agentic AI capabilities across the software development lifecycle. Lead the development of AI agents and multi-agent workflows for requirements, architecture, code generation, testing, review, documentation, deployment, and modernization. Translate engineering standards into secure, scalable, production-ready AI workflows. Hands-on experience building agents with LangChain, LangGraph, AutoGen, CrewAI, or similar frameworks is essential. Using AI coding assistants alone does not meet this requirement. Candidates should describe the frameworks used, their personal implementation work, workflow design, controls, and deployment scope. Locations: San Francisco, CA; Austin, TX; or Dallas area, TX. Exact office location, onsite/hybrid schedule and initial assignment duration will be confirmed during hiring. This is a Java-focused opening; strong Java proficiency is required. Screening will cover 3+ years using AI coding tools in real production development workflows and 3+ years designing and implementing multi-step AI/agentic workflows for SDLC tasks. Please provide dates and concrete examples, distinguishing prototypes from production use.
Required qualifications
- 8+ years of software engineering experience, including strong proficiency in Java and enterprise application development.
- Strong hands-on experience designing and building enterprise AI agents, multi-agent workflows, and GenAI-powered applications.
- Expertise with LangChain, LangGraph, AutoGen, CrewAI, or similar agentic frameworks, supported by concrete implementation examples.
- Experience implementing RAG, vector databases, tool calling, MCP integrations, memory, context management, and multi-agent orchestration.
- Advanced proficiency with Claude Code, GitHub Copilot, Cursor, or similar AI development platforms.
- Strong understanding of prompt/context engineering, structured outputs, evaluation frameworks, guardrails, and hallucination reduction.
- Experience implementing AI-augmented SDLC practices across requirements, architecture, development, testing, review, documentation, deployment, and modernization.
- Ability to design autonomous and human-in-the-loop workflows for code generation, testing, debugging, documentation, and deployment.
- Experience validating AI-generated code and agent outputs for correctness, security, maintainability, scalability, and performance.
- Understanding of responsible AI, enterprise governance, data privacy, access controls, secure agent execution, and auditability.
- Solid foundation in system design, object-oriented programming, data structures, algorithms, databases, APIs, concurrency, cloud platforms, and CI/CD.
- Bachelor's degree in Computer Science or a related field, or equivalent professional experience.
Show responsibilities and moreShow less
Responsibilities
- Lead the design and implementation of agentic AI capabilities across the end-to-end SDLC.
- Architect autonomous and multi-agent workflows for requirements analysis, solution design, code generation, testing, code review, documentation, deployment, and support.
- Build enterprise AI agents using LangChain, LangGraph, AutoGen, CrewAI, or similar frameworks, including tool calling, orchestration, memory, and context management.
- Implement RAG, vector search, MCP integrations, structured outputs, and enterprise knowledge grounding to improve agent accuracy and relevance.
- Establish standards for prompt engineering, context engineering, spec-driven development, agent evaluation, and hallucination reduction.
- Define agent autonomy, decision boundaries, guardrails, human-in-the-loop approvals, security controls, and auditability for production environments.
- Integrate agents with organizational coding standards, architecture patterns, engineering practices, repositories, CI/CD pipelines, and development toolchains.
Preferred qualifications
- Experience with AWS, Azure, or Google Cloud Platform.
- Familiarity with secure coding practices and application security.
- Experience modernizing legacy enterprise applications using AI-assisted and agentic approaches.