Senior Backend Engineer

Job Description

Deep See delivers an open and flexible agentic platform to accelerate AI adoption for financial services in front, middle, and back‑office operations. Our cloud‑based platform seamlessly integrates with existing bank architectures, whether they’re just starting their AI transformation journey or looking to enhance existing in‑house capabilities with Agentic AI solutions. With Deep See’s pre‑trained & pre‑configured agents, banking and capital markets firms can automate and orchestrate manual, repetitive tasks—freeing domain experts for strategic work, reducing risk, and streamlining operations to drive greater efficiency.

We are looking for an experienced and forward‑thinking Sr. Backend Engineer to architect and build high‑performance, scalable backend services as part of a best‑in‑class engineering organization. The role is ideal for someone who thrives in a polygot environment (Java & Python), can tackle complex performance challenges, and is working with and excited about cutting‑edge AI technologies.

• Design and implement scalable microservices using Java (Spring Boot) and Python (FastAPI) in a modern cloud‑native architecture
• Optimize high‑throughput data processing pipelines handling large volumes of emails and documents
• Identify and resolve performance bottlenecks in CPU‑intensive document extraction and processing workflows

• Design complex Postgre
  
  SQL queries and optimize database performance through strategic indexing and query refactoring
• Work with both relational (Postgre
  
  SQL) and No
  
  SQL (e.g., Mongo
  
  DB) databases to ensure efficient data persistence
• Implement robust data pipelines with event‑driven architecture using Kafka
• Eliminate N+1 query patterns and implement efficient data access patterns

• Build and deploy production‑ready agentic AI systems using frameworks (e.g., Semantic Kernel, Lang Chain, Lang Graph, agent‑framework, and SDKs)
• Integrate Azure OpenAI, Azure Foundry and other LLM services into backend processing workflows
• Implement guardrails, tracing, monitoring, and human‑in‑the‑loop systems for AI agent operations
• Design intelligent document extraction and classification systems to enhance automation
• Use transfer learning, model distillation, and ensemble model techniques to create fit‑for‑purpose models that are highly performant and accurate

• Implement comprehensive monitoring, logging, and alerting using Prometheus, Grafana, and distributed tracing tools
• Establish SLO/SLI metrics and performance dashboards for production systems
• Design fault‑tolerant systems with proper error handling, retry logic, and circuit breakers
• Write thorough unit, integration, and smoke tests using JUnit, Mockito, Pytest, and Playwright

• Work closely with Product and Engineering teams to translate requirements into technical solutions
• Conduct code reviews and mentor team members on best practices
• Document architectural decisions (ADRs) and create operational runbooks
• Deep dive technically while also operating at the strategic, organizational level

• 5+ years of backend development experience with strong fundamentals in distributed systems and microservices architecture
• Strong proficiency in Python 3.10+ including asynchronous programming, FastAPI, and async/await patterns
• Solid Java experience (Java 17+) with Spring Boot, Spring Data JPA, and RESTful API development
• Expert‑level SQL skills with Postgre
  
  SQL, including complex query optimization and index design
• Event‑driven architecture experience with Kafka or similar message queue systems
• Testing expertise with JUnit, Mockito, and Pytest for comprehensive test coverage

• Production experience building and deploying agentic AI systems (Lang Chain, Lang Graph, agent‑framework, or similar)
• Strong understanding of LLM integration patterns, prompt engineering, and AI observability/tracing
• Experience with Docker containerization and cloud platforms (AWS/Azure)
• Proficiency with modern development tools:
  Git, uv, Gradle, pre‑commit hooks,…