L #2793
Applications open
Full-Time Job
Software Engineer III - Python LLM Engineer
JPMorgan Chase
About the role
Job Description
We have an exciting and rewarding opportunity for you to take your software engineering career to the next level.
As a Software Engineer III at JPMorganChase within the Asset and Wealth Management Technology team, you are an integral part of an agile team that works to enhance, build, and deliver trusted market-leading technology products in a secure, stable, and scalable way. Drive significant business impact through your capabilities and contributions, and apply deep technical expertise and problem-solving methodologies to tackle a diverse array of challenges that span multiple technologies and applications.
Job Responsibilities
- Design and build agentic AI workflows capable of multi-step reasoning, tool orchestration, and task execution, with clear boundaries, fallback behavior, and human approvals where needed.
- Develop and productionize LLM-powered applications such as conversational interfaces, intelligent search, summarization/extraction services, and advisory assistants.
- Implement patterns for tool integration (APIs, internal services, data sources) so agents can safely retrieve data and take actions with authentication/authorization, audit logging, and least-privilege access.
- Build and maintain RAG components where applicable (ingestion, indexing, retrieval, grounding/citations, reranking) and tune for answer quality and latency.
- Produce architecture/design artifacts for distributed systems, including service boundaries, data flows, scalability, resiliency, and non-functional requirements (latency/throughput/availability).
- Establish evaluation and monitoring: offline test sets, automated regression checks, prompt/version management, hallucination/grounding checks, and runtime observability (traces, latency, cost, tool-call success rates).
- Apply practical data engineering / analytics skills to support AI features: data cleaning, normalization, deduplication, exploratory analysis, and basic KPI reporting on system quality and user behavior.
- Leverages enterprise-authorized AI coding assist tools within the work environment to improve code quality, delivery speed, and productivity across complex deliverables (e.g., code generation/refactoring, unit test creation, documentation), while validating outputs through peer review, automated testing, and secure coding standards; contributes learnings and reusable patterns to improve broader team effectiveness.
- 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.
- Collaborate with product, design, and stakeholders to translate requirements into technical solutions, delivery plans, and iterative releases and ensure solutions meet security, privacy, and responsible AI expectations (safe handling of sensitive data, compliance-aware design, and controlled model outputs).
- Mentor engineers and contribute to shared standards, reusable components, and engineering best practices across AI delivery.
Required Qualifications, Capabilities, And Skills
- Formal training or certification on software engineering concepts and 3+ years applied experience
- Experience in software engineering, including delivering production applications and services.
- Strong proficiency in Python and experience with APIs/microservices.
- Hands-on experience building LLM/RAG/agentic applications (prompting, structured outputs, tool/function calling, state management, error handling).
- Familiarity with agent frameworks such as LangChain, LangGraph, LlamaIndex, Semantic Kernel, CrewAI, AutoGen, or similar.
- Working knowledge of data handling basics: data cleaning, joins/aggregations, simple statistics, exploratory analysis; comfortable with SQL and/or pandas-style workflows.
- Experience with cloud platforms (AWS or Azure), CI/CD, observability, and operational reliability practices.
- Hands-on experience using enterprise-authorized AI-assisted software development tools within the work environment (e.g., for coding, test creation, troubleshooting, or documentation) with demonstrated ability to critically evaluate, validate, and refine AI-generated outputs for correctness, performance, and security.
- Understanding of responsible AI use in engineering workflows, including data sensitivity considerations, secure handling of inputs/outputs, and adherence to resiliency and security expectations; ability to guide peers on safe and effective usage within team practices.
- Strong understanding of secure development practices and validation of AI outputs (correctness, performance, and security).
Preferred Qualifications, Capabilities, And Skills
- Familiarity with vector search and retrieval tuning (embeddings, reranking, query rewriting).
- Experience working in regulated environments or building applications with strict audit/security requirements.
ABOUT US
Eligibility & process
Who can apply
Employment type: Full-time
Skills & stack
Selection process
Details are shared by the recruiter after shortlisting.
Prep kit
20 resourcesStudy material 4
Aptitude Practice Questions & Mock Tests
Curated logical, quantitative, and verbal reasoning problems for the initial online screening round.
Company-Specific Interview Preparation Corner
Detailed interview experiences, exam formats, and previous test questions for JPMorgan Chase and tech roles.
Technical Placement Question Bank
High-yield coding cheat sheets, core CS fundamentals (OOP, DBMS, OS, Networks), and rapid revision guides.
Algorithm, DSA & Live Code Debugger Practice
Hands-on problem sets to improve coding speed and step-by-step memory debugging.
Company-specific guides 4
APTITUDE & LOGIC
Aptitude Practice Questions & Online Mock Tests
Curated logical, quantitative, and verbal reasoning problems to sharpen reasoning skills required for the initial screening test.
COMPANY GUIDE
JPMorgan Chase Interview Preparation Corner
Comprehensive guide covering typical interview formats, common questions, and preparation tips for JPMorgan Chase and off-campus tech roles.
MOCK TESTS & PAPERS
Comprehensive Interview Prep Resources & Syllabus
Collection of previous year questions, company-specific test patterns, and interview experiences for technical and HR rounds.
CODING PRACTICE
Algorithm and Data Structure Problem Set
Practice problems to improve coding proficiency and algorithm problem-solving speed for technical rounds.
Likely coding questions 4
Round-wise strategy 4
Round 1: Online Assessment (OA)
Aptitude, Quantitative Logic & 2 Coding Problems
Focus on accuracy and speed. Practice arrays, strings, and standard arithmetic puzzles.
Round 2: Technical Interview 1
Core Tech Stack (Python, SQL, Next.js, Microservices, AWS, Azure, CI/CD, Generative AI / LLMs) & Live Code Tracing
Explain your thought process aloud. Analyze time & space complexities before coding.
Round 3: System Design & Problem Solving
Database Schemas, APIs & Architecture Basics
Clarify edge cases, diagram schemas cleanly, and discuss scalability trade-offs.
Round 4: HR & Cultural Fit Discussion
JPMorgan Chase Core Values, Learning Agility & Offer Terms
Demonstrate passion, strong communication, and readiness for full-time collaboration.
Technical questions 5
What is the difference between WHERE and HAVING clauses in SQL? Answer
Model answer: WHERE filters rows before any groupings are applied, while HAVING filters aggregated groups after GROUP BY has executed.
Explain SQL Window functions: ROW_NUMBER(), RANK(), and DENSE_RANK(). Answer
Model answer: ROW_NUMBER() assigns unique sequential integers. RANK() assigns identical ranks to ties and skips ranks. DENSE_RANK() assigns identical ranks to ties without skipping rank numbers.
How do you handle NULL and missing values during data cleaning in Python/Pandas? Answer
Model answer: Use .isna().sum() to identify missing values. Impute with mean/median using .fillna() or remove with .dropna(subset=[...]) depending on variance impact.
What is the difference between Star Schema and Snowflake Schema in Data Warehousing? Answer
Model answer: Star Schema has denormalized dimension tables directly connected to the central Fact table. Snowflake Schema normalizes dimension tables into sub-dimensions to minimize redundancy.
How do you calculate MoM (Month-over-Month) growth in SQL? Answer
Model answer: Use LAG(revenue, 1) OVER (ORDER BY month) to fetch the previous month's revenue and compute (revenue - prev_revenue) / prev_revenue * 100.
Behavioural & HR questions 3
Why do you want to join JPMorgan Chase as a Software Engineer III - Python LLM Engineer?
Highlight JPMorgan Chase's market reputation, recent tech innovations, and how your skills in Python directly solve their team's objectives.
Highlight JPMorgan Chase's market reputation, recent tech innovations, and how your skills in Python directly solve their team's objectives.
Describe a challenging bug or academic project roadblock and how you resolved it.
Use the STAR method: Situation (project context), Task (what needed solving), Action (specific tools/logic applied), Result (quantifiable positive outcome).
Use the STAR method: Situation (project context), Task (what needed solving), Action (specific tools/logic applied), Result (quantifiable positive outcome).
How do you handle strict deadlines or sudden scope changes?
Explain your prioritization strategy, proactive communication with mentors/peers, and agile mindset.
Explain your prioritization strategy, proactive communication with mentors/peers, and agile mindset.
Competitive Package
Bengaluru, India
Employment type: Full-time
