Lead Software Engineer - AI and Cloud Platforms

JP Morgan Services India Pvt Ltd; Hyderabad; On-site; INR 3,500,000 - 6,000,000; Full time

Job summary

JP Morgan Services India Pvt Ltd in Hyderabad seeks a Senior AI Architect to design end-to-end AI systems, including LLM-enabled features and RAG workflows. You will define APIs, data flows, and governance-compliant production readiness.

Lead rapid prototyping, evaluate models and tools, and drive enterprise SDLC integration with observability and reliability best practices. Strong collaboration with Product, Data Science, and security teams is required.

Qualifications

• Formal training or certification in software engineering concepts with 5+ years applied experience.
• Formal training or certification in software engineering concepts with 10+ years applied software engineering experience, including 3+ years delivering AI/ML solutions.

Responsibilities

• Architect end-to-end AI systems and workflows (LLM-enabled features, RAG, agentic patterns) with APIs and data flows.
• Lead hypothesis-driven product discovery through rapid prototyping and evaluation to inform roadmap decisions.
• Develop secure, production-grade code and review others’ code for maintainability and performance.
• Define non-functional requirements for AI services (latency, cost, reliability).
• Establish AI quality, validation, regression testing, and guardrails for safe operation.
• Integrate AI capabilities into enterprise applications and SDLC workflows from prototype to production.
• Collaborate with Product, Design, Data Science/ML and governance stakeholders to shape problem statements and success metrics.
• Evaluate models, tools, and vendor solutions for architectural fit and security.
• Automate remediation and improve reliability via observability and incident learning.
• Promote enterprise-approved AI-assisted engineering practices and reusable patterns across the team.

Skills

Java

Cloud Platforms (AWS)

Kafka

Microservices

Python

TypeScript

LLM / AI systems

LangChain / AI frameworks

MLOps / LLMops

Secure coding

AI governance / security

Education

Bachelor's or Master’s in Computer Science

Tools

Docker

Kubernetes

LangGraph

Semantic Kernel

AutoGen

CrewAI

Job description

Job Responsibilities

• Architect end-to-end AI systems and workflows (LLM-enabled features, retrieval-augmented generation (RAG), agentic patterns, decision support), defining APIs, data flows, and operational readiness.
• Lead hypothesis-driven product discovery through rapid prototyping, experimentation, and evaluation to accelerate time-to-learning and inform roadmap decisions.
• Develop secure, high-quality production code and review code written by others to uphold maintainability, performance, and resiliency standards.
• Define non-functional requirements for AI services (latency, cost, reliability, availability) and drive design decisions that meet them.
• Establish AI quality and validation standards, including offline/online metrics, human review, regression testing, and guardrails for safe operation.
• Integrate AI capabilities into enterprise applications and SDLC workflows, ensuring scalable delivery from prototype to production.
• Partner with Product, Design, Data Science/ML, and governance stakeholders to shape problem statements, success metrics, and acceptance criteria.
• Evaluate models, tools, and vendor solutions by assessing architectural fit, control requirements, and integration within existing platforms and information architecture.
• Automate remediation of recurring issues and improve operational stability through observability, incident learnings, and proactive reliability engineering.
• Drives team adoption of enterprise-authorized AI-assisted engineering practices within the work environment to improve code quality, delivery speed, and operational outcomes (e.g., AI-assisted code review/refactoring, test strategy acceleration, incident/root-cause analysis support), while establishing consistent validation standards (secure coding, peer review, automated testing) and promoting reuse of effective patterns across the team.
• Applies knowledge of tools within the Software Development Life Cycle toolchain, including enterprise-authorized AI-assisted development and automation capabilities, to improve the value realized by automation.

Required qualifications, capabilities, and skills

• Formal training or certification on software engineering concepts and 5+ years applied experience.
• Formal training or certification in software engineering concepts with 10+ years of applied software engineering experience, including 3+ years delivering AI/ML and Generative AI solutions in production environments.
• Java, Cloud Platforms (AWS), Kafka, Micro services
• Hands‑on experience designing and delivering LLM solutions, including RAG, embeddings, orchestration/tool calling, and prompt/model optimization.
• Demonstrated expertise building AI agents and agentic workflows (single‑agent and/or multi‑agent patterns) with measurable outcome tracking.
• Advanced programming capability in Python, Java, or TypeScript, with strong code quality and test discipline.
• Practical experience with AI frameworks such as LangChain, LangGraph, CrewAI, Semantic Kernel, AutoGen, or equivalent patterns/tools.
• Proven ability to define evaluation frameworks, guardrails, and validation approaches that address correctness, safety, privacy, and resiliency.
• 3+ years building and operating cloud‑native production services on AWS and/or Azure (GCP experience accepted where applicable).
• Experience with MLOps/LLMOps practices, including model deployment, monitoring, observability, and lifecycle management.
• Demonstrated experience leading effective use of approved AI‑assisted software development tools (e.g., for coding, code review, test acceleration, troubleshooting) with the ability to set team expectations for validating AI outputs for correctness, performance, and security.
• Strong understanding of responsible AI use in engineering workflows, including data sensitivity considerations, secure handling of inputs/outputs, and adherence to resiliency and security expectations; experience coaching engineers on safe, compliant adoption within delivery practices.

Preferred Qualifications

• Experience with vector databases, embeddings, and large‑scale knowledge retrieval architectures, including RAG design patterns and performance optimization.
• Strong background in microservices and cloud‑native architecture, including Docker, Kubernetes, and production‑grade platform engineering practices.
• Proven use of AI‑assisted SDLC practices (e.g., spec‑driven development, AI‑assisted code review/refactoring, test acceleration) with clear human validation and quality controls.
• Knowledge of cybersecurity controls, data sensitivity handling, and AI governance, plus experience leading enterprise modernization and influencing outcomes through technical mentoring and stakeholder management; familiarity with data engineering technologies such as Spark, Kafka, Snowflake, and/or Databricks is a plus.

Experience Level

Senior Level