Lead AI Agent Platform Engineer

Socket.dev; New Jersey; On-site; USD 180,000 - 250,000; Full time

Benefits offered by this job

Healthcare

Wellness centers

Retirement plan

Tuition reimbursement

Mental health support

Financial coaching

Job summary

JPMorganChase in the United States is seeking a Lead Software Engineer for the AI Agent Platform to drive the SDK, agent orchestration, and scalable platform capabilities powering large-language-model-powered agents at scale. You will translate complex problems into production-grade solutions and collaborate with product and stakeholders to deliver measurable outcomes.

You will own building blocks for agent orchestration, tool calling, retrieval-augmented generation, and memory, while

Qualifications

• Formal training or certification on applied artificial intelligence and machine learning concepts and 5+ years applied experience.
• Advanced proficiency in Python with strong software engineering fundamentals, including testing, design patterns, version control, and code review practices.
• Hands-on experience building, evaluating, and deploying machine learning or large-language-model-enabled systems into production environments—ideally reusable libraries, SDKs, or platform services consumed by other engineering teams.
• Practical experience with prompt engineering and retrieval-augmented generation, including building evaluation methods, benchmarks, and quality measurement to systematically improve capabilities such as NL2SQL and RAG.
• Experience designing and operating reliable services, including incident response readiness, performance tuning, and operational stability for data-intensive systems.
• Demonstrated ability to lead technical decisions and deliver outcomes through ambiguity, balancing speed, risk, and long-term maintainability.
• Strong communication skills with the ability to explain technical trade-offs to both technical and non-technical stakeholders.

Responsibilities

• Lead end-to-end delivery of the AI Agent Platform SDK and frameworks—from problem framing and technical design through production deployment, scaling, and monitoring that engineering teams use to build, evaluate, and operate AI agents.
• Own core platform services and reusable building blocks: agent orchestration, tool/function calling, retrieval-augmented generation pipelines, and model-serving integration.
• Build and operate first-class agent modalities on the platform, including voice agents, document-extraction agents, and agentic memory.
• Drive systematic hill-climbing of core agent capabilities—including NL2SQL, RAG, voice, document extraction, and tool use—by building evaluation datasets, benchmarks, and quality metrics.
• Establish engineering standards through hands-on system design, rigorous code review, and mentorship to improve reliability, maintainability, latency, and developer experience.
• Build and operationalize evaluation, testing, and observability capabilities (offline eval harnesses, regression suites, tracing, latency and cost telemetry, logs, and analytics) to continuously improve solution quality.
• Implement robust safety and governance patterns—guardrails, content filtering, prompt-injection defenses, access controls, and audit-ready operational practices aligned to enterprise expectations.
• Partner with product managers and stakeholders to shape the roadmap, define success metrics, and prioritize work that delivers measurable business impact.
• Drive cross-functional alignment across engineering, data, security, and risk partners to ensure the platform is secure, stable, performant, and scalable.
• Contribute to technical documentation, SDK references, reference implementations, and enablement content that accelerates adoption and responsible usage.

Skills

Python

LLM/AI platforms

Software design

Testing & CI/CD

Cloud platforms

Incident response

Tools

Docker

Kubernetes

LangGraph

LlamaIndex

Google ADK

Job description

JPMorganChase in the United States is seeking a Lead Software Engineer for the AI Agent Platform to drive the SDK, agent orchestration, and scalable platform capabilities powering large-language-model-powered agents at scale. You will translate complex problems into production-grade solutions and collaborate with product and stakeholders to deliver measurable outcomes.

You will own building blocks for agent orchestration, tool calling, retrieval-augmented generation, and memory, while