RemoteLeaf Logo
Log in Sign up

Senior Engineer AI

16 hours, 2 minutes ago
India
Full-time
Senior
AI Engineer
Software Development
AWS CI/CD Docker FastAPI Flask GCP Go JSON Kubernetes LLM Next.js Node.js PostgreSQL Python RabbitMQ Redis TypeScript XML
Apply Now
Delta Exchange

Delta Exchange

Delta Exchange is a leading digital asset derivatives exchange offering futures, perpetuals, and options trading with up to 100x leverage on Bitcoin, Ethereum, and 100+ Altcoins.

Capital Markets
11-50
Founded 2018
View All Jobs 2

Description

  • Design, build, and maintain production AI applications end-to-end across backend, frontend, and inference services.
  • Architect and optimize RAG systems using vector databases, embedding models, and chunking or indexing strategies.
  • Build agentic workflows with tool calling, multi-step reasoning, and structured output parsing.
  • Write and iterate on system prompts, few-shot examples, and prompt chains to improve output quality.
  • Implement function calling, tool-use patterns, and structured JSON or XML output handling with LLM provider APIs.
  • Optimize inference costs through model selection, caching, token budgeting, request batching, and prompt compression.
  • Build evaluation frameworks to measure accuracy, relevance, hallucinations, and regressions across prompt and model changes.
  • Deploy and manage AI services on Kubernetes with CI/CD pipelines in AWS or GCP.
  • Integrate AI capabilities with third-party platforms such as Telegram bots and chat widgets.
  • Contribute to architectural decisions around model selection, hosting strategy, and build-vs-buy trade-offs.

Requirements

  • 5+ years of experience shipping production software systems.
  • 2+ years of experience building AI or LLM-powered applications end-to-end for real users and meaningful volume.
  • Strong experience with RAG architectures, including vector databases, embeddings, chunking, indexing, and retrieval evaluation.
  • Deep understanding of LLM capabilities and limitations, including prompt engineering, tool calling, structured outputs, context window management, and multi-turn conversations.
  • Experience with LLM provider APIs and abstraction layers such as OpenAI, Anthropic, LiteLLM, or OpenRouter.
  • Proficiency in Python with Flask or FastAPI and/or Node.js or TypeScript with Next.js and Vercel AI SDK.
  • Hands-on experience building evals, tracking quality metrics, and debugging non-deterministic outputs in production.
  • Familiarity with cost optimization techniques such as model routing, caching, token usage monitoring, and prompt compression.
  • Solid fundamentals in data structures, algorithms, and system design.
  • Experience with Docker, Kubernetes, and cloud platforms such as AWS or GCP.
  • Practical understanding of Kubernetes concepts and trade-offs.
  • Experience with observability tools such as Sentry or Opik.
  • Experience with agentic frameworks such as Vercel AI SDK, LangChain, or Mastra is preferred.
  • Experience building GenAI apps using raw HTTP calls to provider APIs and designing conversation persistence is preferred.
  • Background in fine-tuning or training open-source models is preferred.
  • Knowledge of cryptocurrency, derivatives trading, or financial systems is preferred.
  • Open-source contributions or personal projects with real traction are preferred.

Interested in this position?

Apply directly on the company website

Apply Now

Similar Roles

HighLevel

Lead Engineer - Social Planner - Full stack

HighLevel 251-1K Internet Software & Services

HighLevel is seeking a Lead Engineer to own the Social Planner and Media Optimization products, guiding a distributed team to improve reliability, scalability, and performance for high-volume social publishing and analytics workflows.

India Full-time Lead Full-stack Engineer Technical Lead
Angular CI/CD ClickHouse Elasticsearch Grafana Microservices MongoDB Node.js OAuth OpenTelemetry Prometheus React Redis TDD Vue.js
4 hours, 32 minutes ago
Endpoint User Activity Monitoring Software

Principal Full Stack Developer with React (Remote, Global)

Endpoint User Activity Monitoring Software 51-250 IT Services

Teramind is hiring a Principal Full-Stack Developer to build and lead work on a global remote SaaS platform focused on user behavior analytics, insider risk management, and workforce intelligence.

Ukraine Full-time Lead Full-stack Engineer
$104k-$135k
CI/CD Docker Express.js GraphQL LLM Machine Learning NestJS Next.js PostgreSQL React Tailwind CSS
4 hours, 47 minutes ago
Spear AI

Full-Stack Engineer

Spear AI 11-50 Life Sciences Tools & Services

Spear AI is hiring a Full-Stack Engineer in Washington, DC to build and deploy end-to-end web applications for national security systems across highly secure cloud and edge environments.

United States Full-time Mid Level Full-stack Engineer
AWS Docker GitHub GitHub Actions GraphQL JWT Kafka Kubernetes MySQL Next.js Node.js OAuth PostgreSQL Pulumi Python React REST API SQL Tailwind CSS Terraform TypeScript
5 hours, 2 minutes ago
Influur

AI Data Engineer

Influur 11-50 Media

Influur is hiring an AI Data Engineer in New York/remote to own the full data-to-agent pipeline behind its autonomous viral marketing system for influencer campaigns.

United States Full-time Lead AI Engineer Data Engineer
$200k-$200k
AWS GCP LLM Python
5 hours, 2 minutes ago

You're on a roll! Sign up now to keep applying.

Sign Up

Already have an account? Log in

Used by 14,729+ remote workers