AI Engineer III

Ideal Candidate Profile

5 to 7 years of backend engineering experience

Strong Python OR Java

2 to 3+ years of hands-on Generative AI/LLM experience

Experience building AI-powered applications (RAG, Agentic AI, LLM workflows)

Good understanding of cloud, CI/CD, and backend architecture

Strong system design skills

Role Overview:

We are hiring an engineer to design and build AI-powered tools that improve software engineering and operational workflows across multiple product teams.

You will partner closely with technical leads and engineers to understand their priorities, codebases, architecture, deployment processes, and recurring sources of engineering toil. You will translate those needs into practical AI solutions that teams adopt.

The role spans applied AI domains including developer productivity, workflow automation, retrieval and knowledge systems, agentic workflows, and intelligent engineering tools. You will also ensure that the systems you build are evaluated, observable, reliable, and secure enough to support daily engineering work. This is a hands-on engineering role with substantial cross-team collaboration. Strong communication skills are essential. You must be able to gather requirements from technical leads, ask effective questions, explain and defend technical trade-offs, negotiate scope, and document decisions clearly.

Required Qualifications:

• Strong software engineering experience building production applications, developer tools, automation systems, internal platforms, or data-intensive services.
• Proficiency in Python, TypeScript, Java, or another language suitable for AI applications and backend engineering.
• Practical experience building and delivering LLM-powered applications.
• Experience implementing at least one of the following: Retrieval-augmented generation or enterprise search systems, Agentic or multi-step AI workflows, AI-powered developer or operational tools, Workflow automation spanning multiple APIs or systems, Evaluation and monitoring systems for AI applications.
• Experience integrating software with services such as Git, CI/CD systems, issue trackers, documentation platforms, logging systems, feature-flag platforms, or messaging tools.
• Strong understanding of APIs, testing, debugging, observability, authentication, error handling, and secure software delivery.
• Ability to build working knowledge of unfamiliar systems by reading code and documentation and collaborating directly with system owners.
• Experience taking ambiguous problems through discovery, technical design, implementation, validation, rollout, and adoption.
• Ability to make, communicate, and defend technical trade-offs while balancing delivery speed, reliability, maintainability, cost, and user needs.
• Strong written and verbal communication skills, including experience working directly with technical leads and senior engineers.
• Ability to work independently, manage changing priorities, and deliver across several teams and codebases.

Preferred Qualifications:

Experience in any relevant subset of the following areas is valuable. Candidates are not expected to have used every technology or technique listed.

• Agent frameworks and orchestration: Experience with LangGraph, OpenAI Agents SDK, or LangChain.
• RAG and knowledge systems: Experience with semantic or hybrid retrieval, embeddings, reranking, and working with sources such as Git, Confluence, or Jira.
• Code intelligence and search: Familiarity with source-code indexing, dependency graphs, change-impact analysis, and platforms such as OpenSearch or Elasticsearch.
• Agentic system design: Experience with planning, tool use, memory, retries, and human approval workflows.
• Developer tooling and coding agents: Familiarity with Claude Code, Cursor, or GitHub Copilot, along with repository instructions or IDE integrations.
• Tool integration and automation: Experience using function calling, APIs, or event-driven workflows to automate engineering and operational tasks.
• Evaluation and observability: Experience with synthetic evaluations, regression testing, LLM-as-judge methods, and platforms such as LangSmith or OpenTelemetry.
• Models, reliability, and security: Familiarity with Anthropic, OpenAI, or Amazon Bedrock, along with structured outputs, guardrails, and secure data handling practices.
• Systems and infrastructure: Experience deploying AI applications using containers, APIs, or workflow engines.
• Deployment and impact: A track record of shipping AI tools into real engineering workflows and measuring their impact developer productivity, software quality, reliability, cost, or operational outcomes.

Primary Skills: Python and Java, Experience delivering LLM-powered applications, Agentic or multi-step AI workflows

Secondary Skills: Understanding of APIs, testing, debugging, observability, authentication, error handling