Coba is currently recruiting on behalf of one of our long-established clients—a leading global trading and investment firm. We are seeking a talented Full-Stack LLM Application Engineer to help design, build, and scale AI-powered chatbot applications that support high-performance trading, middle office, and back office operations.

This is a hands-on engineering role where you’ll take full ownership of the application stack—from intuitive chat interfaces to secure APIs and backend integrations. You’ll collaborate closely with data scientists and platform engineers to deliver real-time, secure, and scalable AI services in a dynamic, enterprise-grade environment.

Key Responsibilities:

• Chat UI Development:
  Build responsive, user-friendly chat interfaces using React and TypeScript, supporting both desktop and mobile. Implement secure authentication via OAuth/OIDC and support chat and semantic search patterns.

• API & Model Serving:
  Serve LLMs through FastAPI-based REST/gRPC endpoints. Deploy models using Triton, Ray Serve, or SageMaker with GPU-aware autoscaling.

• Security & Access Control:
  Enforce fine-grained access controls using OAuth claims. Implement prompt validation, rate limiting, and detailed audit logging.

• Legacy System Integration:
  Develop low-latency interfaces to connect with existing systems built in Java/.NET, as well as protocols like FIX, Kafka, and message queues.

• Monitoring & Cost Optimization:
  Set up dashboards to monitor latency, model accuracy, and usage metrics. Manage CI/CD pipelines using GitLab for safe, blue-green deployments.

• Infrastructure Automation:
  Contribute to Terraform modules for provisioning and managing AWS infrastructure, including EKS clusters, API Gateways, and Lambda functions.

Technical Skills Required:

• Languages & Frameworks: Python, FastAPI, React, TypeScript, LangChain/Haystack
• Model Ops: Hugging Face, AWS Bedrock SDK, Triton Inference Server, Ray Serve, SageMaker
• Authentication: OAuth2, OIDC, SSO
• Data Stores: SQL, pgvector, Pinecone, OpenSearch
• Infrastructure: Docker, Kubernetes (EKS), Terraform, GitLab CI
• Observability: Prometheus, Grafana
• Protocols: REST, gRPC, WebSockets, SSE

What We’re Looking For:

• 4+ years of experience building cloud-native, user-facing applications—ideally in trading or financial services
• Proven experience deploying LLMs or deep learning models in production
• Strong communication skills and the ability to present technical solutions to both engineering and executive teams
• A proactive, ownership-driven mindset with a passion for building secure, scalable systems in fast-moving environments

Ready to shape the future of AI in financial services?
Apply now to join a team that’s pushing the boundaries of innovation in one of the world’s most dynamic industries.