Senior Engineer AI
Delta Exchange is a cryptocurrency derivatives exchange offering futures, options, and leveraged trading. They have a referral program allowing users to earn commissions from the trading fees of referred users.
Funding history
Investors
About Delta Exchange
Delta Exchange is a derivatives trading platform that offers features like futures, options, and leveraged trading for virtual digital assets. It provides a referral program where users can earn a commission on the trading fees paid by their invited friends. The platform is operated by Excelium Technologies Private Limited, a FIU (Govt. of India) registered entity.
Skills
Candidate Availability
Required and preferred rules are kept separate and reflect the wording in the original posting.
About the Role
Own and evolve production AI applications across backend, frontend, and inference services, including RAG systems, agentic workflows, prompt engineering, inference-cost optimization, evaluations, Kubernetes operations, and third-party AI integrations.
Requirements
- 5+ years shipping production software systems.
- 2 years building AI/LLM-powered applications end-to-end with real users and volume.
- Strong experience with RAG architectures, vector databases, embedding models, chunking/indexing, and retrieval evaluation.
- Deep understanding of LLM capabilities and limitations, prompt engineering, function/tool calling, structured outputs, context windows, and multi-turn conversations.
- Experience with LLM provider APIs and abstraction layers such as OpenAI, Anthropic, LiteLLM, or OpenRouter.
- Proficiency in Python with Flask/FastAPI and/or Node.js/TypeScript with Next.js and Vercel AI SDK; Golang is a plus.
- Hands-on experience building evaluations, tracking quality metrics, and debugging nondeterministic production outputs.
- Familiarity with cost optimization techniques including model routing, caching, token monitoring, and prompt compression.
- Solid fundamentals in data structures, algorithms, and system design.
- Experience with Docker, Kubernetes, AWS, and GCP; practical Kubernetes knowledge is required.
Responsibilities
- Design, build, and maintain production AI applications end-to-end across backend, frontend, and inference services.
- Architect RAG systems using vector databases, embedding models, and chunking strategies optimized for accuracy and latency.
- Build agentic workflows with tool and function calling, multi-step reasoning, and structured output parsing.
- Write and iterate system prompts, few-shot examples, and prompt chains.
- Implement function calling, tool-use patterns, and structured JSON/XML output handling.
- Drive cost optimization through model selection, caching, token budgeting, and request batching.
- Build evaluation frameworks measuring accuracy, relevance, hallucination rates, and regressions using observability tools.
- Work with RabbitMQ, Redis, and PostgreSQL for AI service backends.
- Deploy and manage AI services on Kubernetes with CI/CD pipelines on AWS and GCP.
- Integrate AI capabilities with Telegram bots, chat widgets, and other third-party platforms.
- Contribute to architectural decisions involving model selection, hosting, and build-versus-buy trade-offs.
