Senior Lead Software Engineer- Python AI

JPMorganChase•Plano, TX

About The Position

The Senior Lead Software Engineer will enhance products across the product line by identifying, prioritizing, and delivering AI-driven features that improve user experience, efficiency, and operational resilience. The role involves designing, building, and deploying production-grade AI applications, including LLM-powered workflows, Retrieval-Augmented Generation (RAG) solutions, and agentic systems with enterprise-ready controls. The engineer will architect AI systems with production requirements in mind, including latency, scalability, cost management, model selection, observability, reliability, and failure modes. They will establish AI engineering standards, contribute to architecture reviews and reference architectures, and identify and mitigate AI lifecycle risks such as privacy, security, bias, misuse, prompt injection, and vendor risk. This hands-on technical leadership role partners with product, design, risk, legal/compliance, and engineering stakeholders; leads vendor and platform evaluations; researches emerging AI capabilities; and enables teams through documentation, workshops, design reviews, and coaching. The role also includes writing secure, high-quality production code, reviewing and debugging others’ code, and driving alignment and end-to-end outcomes across teams without direct authority.

Requirements

Formal training or certification in software engineering concepts.
At least 5 years of applied engineering experience.
Hands-on experience delivering AI-powered features in production or near-production environments, such as LLMs, RAG, agents, workflow automation, or decision support systems.
Strong proficiency in Python and the ability to build maintainable services, libraries, and pipelines.
Experience building APIs and services with Django, FastAPI, or similar frameworks.
Experience building modern UIs with React or similar frameworks, or strong ability to partner with frontend teams.
Strong system design skills emphasizing secure distributed systems, reliability, and operational excellence.
Practical understanding of Responsible AI and model risk concepts, including evaluation, guardrails, privacy, bias, explainability where applicable, and safe deployment practices.
Experience implementing observability with logging, metrics, and tracing, as well as AI-specific monitoring for quality, drift signals, latency, cost, and error rates.
Experience with cloud platforms; AWS is preferred.
Strong problem-solving skills and a structured, evidence-based approach; comfort working in ambiguity and delivering iteratively.

Nice To Haves

Experience with AI orchestration and agent frameworks such as LangChain, LlamaIndex, Semantic Kernel, or CrewAI.
Experience with vector search and retrieval patterns using tools such as pgvector, Pinecone, Weaviate, or OpenSearch/Elastic.
Experience designing and operating RAG systems, including chunking strategies, retrieval evaluation, citation/attribution patterns, caching, and fallback behaviors.
Familiarity with AI governance and standards, including model documentation, risk assessments, control frameworks, and secure-by-design patterns, and applying them within real delivery timelines.
Strong Infrastructure-as-Code experience, such as Terraform, and CI/CD practice.
Experience with data engineering ecosystems such as Databricks, streaming, data quality controls, and lineage concepts.

Responsibilities

Enhance products across the product line by identifying, prioritizing, and delivering AI-driven features.
Design, build, and deploy production-grade AI applications, including LLM-powered workflows, RAG solutions, and agentic systems.
Build agentic workflows with enterprise-ready identity, authorization, guardrails, tracing, evaluation, and auditability controls.
Develop automation that reduces manual effort and recurring operational issues, including self-healing patterns and intelligent triage.
Architect AI systems for latency, scalability, cost management, model selection, observability, reliability, and failure modes such as hallucinations and tool errors.
Establish and apply AI engineering standards for prompting, RAG design, evaluation, logging and telemetry, and release readiness.
Drive AI architecture reviews and contribute reference architectures for model hosting, orchestration, data access, and secure tool execution.
Identify and mitigate AI lifecycle risks, including data privacy, security, bias, model misuse, prompt injection, and third-party/vendor risk; ensure appropriate documentation and controls.
Partner with product, design, risk, legal/compliance, and engineering stakeholders to align outcomes, constraints, and measurable success metrics.
Lead technical evaluations of vendors and platform providers, assessing capabilities, integration fit, security posture, and total cost of ownership.
Research emerging AI models, frameworks, and tools and translate findings into guidance, prototypes, and adoption recommendations.
Enable teams through documentation, workshops, design reviews, and coaching to improve AI fluency and delivery consistency.
Develop creative software solutions, troubleshoot technical problems, write secure production code, and review and debug code written by others.
Influence stakeholders and align teams without direct authority while owning outcomes end-to-end.