Role Overview :

As a Principal Software Engineer, you will work closely with engineering teams and enterprise architecture to design and deliver high quality, scalable technology solutions. You will be given the autonomy to lead, design, and implement innovative solutions addressing some of the most complex technical challenges in the banking industry.

Serving as a peer technical leader, you will drive cutting edge initiatives across a broad range of platforms as continues its transformation toward innovation, automation, and enhanced customer experience.

We are seeking a Principal Engineer with deep expertise in Generative AI (GenAI) and agentic systems, focused on embedding intelligent agents and AI driven workflows directly into the Software Development Life Cycle (SDLC). This role will help advance automation, decision making, and developer productivity across engineering platforms.

Key Responsibilities :

Technical Leadership & Engineering Excellence :

- Act as a hands on technical leader within an Agile environment, promoting engineering best practices and effective collaboration.

- Contribute thought leadership to solution design and architectural discussions, ensuring alignment with enterprise architecture standards.

- Design, develop, and implement modern, architecturally sound software components, tools, and applications to support strategic business objectives.

- Embed quality attributes including scalability, reliability, maintainability, and observabilityinto distributed, service based architectures.

- Apply industry best practices to proactively identify, remediate, and prevent security vulnerabilities throughout the SDLC.

- Serve as a peer leader and mentor, fostering a culture of innovation, accountability, and technical excellence.

Generative AI & Agentic Systems :

- Design and implement GenAI powered applications and agentic workflows embedded within SDLC tools and engineering processes.

- Build and scale Retrieval Augmented Generation (RAG) pipelines, including document ingestion, embeddings, and contextual retrieval at enterprise scale.

- Develop APIs, microservices, and integration layers enabling AI driven automation across engineering platforms and CI/CD pipelines.

- Implement and optimize vector database solutions (e.g., Pinecone, Weaviate, Milvus) for semantic search and enterprise knowledge retrieval.

- Partner with Product, Architecture, Security, and DevOps teams to embed AI capabilities into build, test, and release workflows (e.g., gated PR checks, automated code reviews, test generation).

- Ensure compliance with security, privacy, and responsible AI standards, including model evaluation, guardrails, and human in the loop review processes.

- Establish observability for AI systemstelemetry, tracing, evaluation harnessesto monitor accuracy, drift, latency, and cost, driving continuous improvement.

Core Capabilities :

- Drives the adoption of agentic flows and Gen AI practices to solve business problems and improve delivery quality and cycle time.

- Demonstrate day-one readiness to operate in the new model adopting new tools and technologies at the expected velocity.

- Learning agility is paramount and candidates who can adapt quickly to new technologies will be given preference.

Required Qualifications :

- 8+ years of hands on software engineering experience delivering commercial software products.

- Demonstrated ability to lead, influence, and mentor senior software engineers.

- 5+ years of experience working with big dataquerying, analyzing, and managing large scale datasets.

- Proficiency in multiple programming languages, including at least one modern front end framework (Angular, React, or Vue), and languages such as Python, Java, JavaScript, Ruby, Go, C/C++.

- Strong cloud experience with AWS, Azure, or GCP, including handling sensitive and regulated data.

- Experience with Linux/Bash, CI/CD pipelines (Jenkins, CircleCI, GitHub Actions, or equivalent), and modern DevOps practices.

- Hands on experience with LLM frameworks and services (e.g., OpenAI, AWS Bedrock/SageMaker, Hugging Face, LangChain/LangGraph).

- Deep understanding of RAG techniques, embedding models, and vector databases.

- Familiarity with LLM deployment, prompt engineering, fine tuning, evaluation, and guardrail techniques.

- Experience with containerization and orchestration technologies (Docker, Kubernetes).

- Strong understanding of responsible AI, privacy, and security considerations for production AI systems.