J

JP Morgan Chase

Runs a consumer bank and an investment bank

Senior Lead Software Engineer - AI Agents

AI Application EngineeringConfirmed live in the last 24 hours
Full-timeBuenos Aires, ArgentinaNo salary listedIn-person

About the Job

Requirements

  • At least 8 years of software engineering experience, including at least 2 years shipping production LLM- or agent-based systems to real users.
  • Deep hands-on expertise in Python and comfort with at least one other modern language: TypeScript, Java, or Go.
  • Practical, current experience with agentic technologies, including LLM orchestration, tool or function calling, retrieval-augmented generation, evaluation harnesses, guardrails, prompt and model versioning, and model gateways.
  • Hands-on experience with Model Context Protocol architectures, including designing servers and clients, tool schemas, capability negotiation, and secure enterprise deployment patterns.
  • Experience building and operating production-grade backend or distributed systems, including APIs, queues, workers, observability, and on-call support.
  • Strong grounding in data platforms such as Databricks or Snowflake, lakehouse patterns, and modern MLOps or LLMOps, including CI/CD, feature, prompt, and model registries, and telemetry.
  • Practical experience with responsible AI, security, and controls for enterprise deployments, including personally identifiable information handling, red-teaming, prompt-injection defense, and secret and tool-use hygiene.
  • Ability to write design documents, provide substantive pull request reviews, and explain trade-offs to non-technical stakeholders.
  • A bachelor's degree in Computer Science or a related discipline, or equivalent industry experience.

Responsibilities

  • Own the end-to-end design of production agents, including planners, tools, memory, retrieval (RAG or GraphRAG), guardrails, human-in-the-loop processes, and evaluators.
  • Implement the team's Model Context Protocol stack by writing MCP servers and clients, defining tool schemas, negotiating capabilities, and integrating securely with enterprise systems.
  • Select an appropriate orchestration pattern for each use case, such as single-agent, planner-executor, supervisor-worker, or debate/critique, and avoid unnecessary complexity.
  • Build and maintain agent evaluation harnesses, including gold sets, offline benchmarks, LLM-as-judge with human calibration, online A/B testing, and regression gates in CI/CD.
  • Instrument agents with business and quality KPIs, including deflection rate, time-to-resolve, CSAT, cost per interaction, task success, groundedness, refusal correctness, and safety incidents.
  • Partner with cyber, privacy, and model risk teams to implement guardrails for personally identifiable information, prompt injection and jailbreak defense, tool-use hygiene, secret handling, and prompt and model version pinning.
  • Own agent SLOs and error budgets, write runbooks, and participate in the on-call rotation.
  • Build canaries, circuit breakers, deterministic replay, and rollback paths for prompts, models, and tools.
  • Diagnose and fix production issues end-to-end, including token-spend anomalies, tool-call failures, and hallucination regressions.
  • Contribute improvements to the shared agentic platform, including orchestration, model gateway, vector and knowledge stores, telemetry, and evaluation harnesses, so other squads can benefit.
  • Write design documents, patterns, and internal blog posts, and represent the team in architecture reviews.
  • Set the technical bar in the squad through code reviews, pairing, and design reviews.
  • Mentor mid-level and junior engineers.
  • Interview candidates and help sustain a strong hiring bar.

Desired Qualifications

  • Experience building employee-facing or workforce productivity products at scale, such as IT service desks, HR technology, knowledge management, or workplace assistants.
  • Experience integrating with ServiceNow, identity providers, endpoint management, and enterprise search.
  • Experience with multi-agent patterns, including planner-executor, supervisor-worker, and debate/critique, and with long-horizon workflows.
  • Contributions to open source, especially in the MCP, agent, or evaluation ecosystem; published research; patents; or public talks in AI, agents, or SRE.
  • Prior experience in a highly regulated environment, such as financial services, healthcare, or the public sector, with model risk management such as SR 11-7 or equivalent.
  • A master's or PhD in a quantitative discipline.

About the Company

JP Morgan Chase

Runs a consumer bank and an investment bank

JPMorgan Chase runs the largest bank in the United States, which serves households and small businesses as Chase and large companies, governments, and investors as J.P. Morgan. During the 2008 financial crisis it bought the failing investment bank Bear Stearns and lender Washington Mutual, and in 2023 it took over First Republic Bank after regulators seized it. Chase takes deposits and earns interest on credit cards, mortgages, and car loans, while the investment side earns fees for advising on mergers, raising money for companies, trading stocks and bonds, and managing wealth. Formed in a 2000 merger, JPMorgan Chase traces its roots to 1799 and is based in New York City.

Company size
10,001+
Company stage
IPO
Headquarters
New York City, New York
Founded
1799

Recently Posted Jobs

Explore more opportunities at JP Morgan Chase

See more jobs