Principal Software Engineer — AI & Data Engineering
JPMorgan Chase1 month ago
Bengaluru, IndiaStaff+
Responsibilities
- Design, implement, test, deploy, operate, debug, monitor, and improve production AI-native services, agent systems, APIs, automation services, data pipelines, and cloud-native components.
- Build reliable agent and multi-agent systems with Google ADK, MCP, or equivalent frameworks, including secure tool exposure, prompts, resources, context, knowledge sources, and reusable capabilities.
- Develop ingestion, transformation, curation, metadata enrichment, retrieval, vector/search, data-quality, connector, and integration pipelines for AI grounding.
- Implement tool calling, planner/executor workflows, memory, state management, human-in-the-loop review, approval gates, access controls, audit trails, guardrails, and safe-failure behavior.
- Own observability, tracing, telemetry, evaluation, regression testing, prompt and version management, drift monitoring, incident response, runbooks, resiliency testing, performance tuning, and cost optimization.
- Drive architecture and code reviews, debugging sessions, incident analysis, technical spikes, reference implementations, mentoring, and delivery-quality accountability.
- Lead adoption of agentic AI-enabled engineering workflows and standards for validation, auditability, traceability, secure data handling, and responsible AI.
- Partner with product, engineering, platform, risk, security, control, and business stakeholders to create engineering roadmaps and production systems.
Requirements
- Formal training or certification in software engineering concepts and 7+ years of applied experience.
- Production experience architecting, developing, deploying, operating, debugging, and improving AI systems, agentic services, APIs, automation services, and cloud-native workloads.
- Deep hands-on experience with Google Agent Development Kit (ADK) and Model Context Protocol (MCP), or equivalent production depth with LangGraph, CrewAI, OpenAI Agents SDK, AutoGen/Microsoft Agent Framework, Semantic Kernel, LangChain, LlamaIndex, or similar ecosystems.
- High proficiency in Python and practical experience with AI and ML engineering frameworks such as LangChain, LlamaIndex, PyTorch, Hugging Face, or equivalent libraries.
- Experience designing prompts, tool instructions, few-shot examples, reusable prompt patterns, and chained workflows as versioned, tested, traceable engineering assets.
- Experience connecting models and agents to enterprise knowledge using embeddings, vector stores, search, retrieval pipelines, ranking, grounding, context assembly, and evidence-based response generation.
- Experience evaluating models, retrieval strategies, hosted APIs, self-managed deployments, caching, batching, routing, fallback patterns, and LLM or agent behavior across quality, latency, resilience, cost, policy compliance, and tool-use accuracy.
- Experience implementing responsible AI and security controls, including approval and escalation flows, output validation, sensitive-data handling, prompt-injection resistance, secure tool use, decision traceability, and custom MCP servers, tools, connectors, and registries.
- Preferred experience with FINOS CALM or similar architecture models and with operating repositories or artifact stores for architecture metadata, reusable patterns, controls, compliance evidence, governance workflows, and dependencies.
- Preferred experience with model deployment, model registries, evaluation pipelines, scalable serving, production AI operations, and model/runtime observability.
Benefits
- The position is part of JPMorgan Chase’s Cloud Foundational Services organization aligned to Infrastructure Platforms.
- JPMorgan Chase is an equal opportunity employer that supports workplace diversity, inclusion, and reasonable accommodations.
Categories
About JPMorgan Chase
JPMorgan Chase provides consumer and commercial banking, payments, credit card, wealth management, and corporate and investment banking services to individuals, businesses, institutions, and governments. The public company (NYSE: JPM) earns revenue from interest, fees, trading, and asset management across operations in more than 100 markets. Headquartered in New York City with roots dating to 1799, it serves retail customers and prominent corporate and government clients through brands including Chase and J.P. Morgan.