Senior AI Engineer - Python, AWS, FastAPI

JPMorgan Chase & Co. is seeking a seasoned Software Engineer III with a specialization in AI Engineering to join our Consumer and Community Banking team in Pune, Maharashtra. In this critical role, you will be an integral part of an agile team, responsible for designing and delivering secure, stable, and scalable market-leading technology products. You will drive crucial technology solutions across various business functions, aligning with the firm's strategic objectives.

Key responsibilities include:

• Developing production-ready FastAPI applications and RESTful APIs to serve AI models and orchestrate complex workflows.
• Designing and implementing Retrieval-Augmented Generation (RAG) systems that integrate large language models (LLMs) with external knowledge for advanced information retrieval.
• Building autonomous AI agent systems capable of multi-step reasoning, tool utilization, and dynamic decision-making.
• Optimizing AI pipelines for latency, throughput, and cost-efficiency.
• Writing clean, maintainable, and well-tested code (unit, integration, end-to-end).
• Leading technical design reviews and contributing to architectural decisions for scalable microservices.
• Planning and implementing robust cloud infrastructure on AWS for maximum reliability and performance.
• Establishing best practices for deployment, monitoring, and incident response.
• Evaluating and integrating emerging AI/ML technologies and frameworks.
• Collaborating with ML engineers, data scientists, and product teams to translate requirements into effective technical solutions.
• Mentoring and supporting junior engineers through code reviews and technical guidance.
• Documenting systems and knowledge to foster team collaboration and continuous improvement.

This role requires a strong foundation in software engineering concepts with 3+ years of applied experience. You must be proficient in Python, with a proven track record of shipping FastAPI applications to production. Experience building and deploying RAG systems, understanding vector databases, embeddings, and retrieval strategies is essential. Hands-on experience with agentic AI systems, LLM orchestration, and multi-agent frameworks is highly desirable. You should excel at system design, capable of architecting complex systems and optimizing for scalability and reliability. Deep knowledge of AWS core services and cloud-native architecture patterns is expected, along with an active AWS Cloud Certification. Strong fundamentals in data structures, algorithms, and distributed systems are required. Familiarity with vector databases (e.g., Pinecone, Weaviate, Milvus) and embedding models is a plus. Proficiency with containerization (Docker) and infrastructure-as-code (Terraform) is necessary. A solid understanding of CI/CD pipelines and modern DevOps practices, along with experience in testing frameworks, is crucial. Excellent communication, proactive problem-solving, and a collaborative team-player attitude are key to success. As a curious learner, you will stay current with AI/ML advancements and best practices, demonstrating a growth mindset and a willingness to mentor others.