AI Engineer

• Design, build, and deploy production-ready Generative AI and LLM-powered applications
• Develop chatbots, copilots, intelligent automation tools, and AI-assisted workflows
• Build and optimize RAG pipelines using embeddings, vector search, and structured or unstructured data
• Integrate LLM platforms such as OpenAI, Anthropic, Azure OpenAI, and similar providers
• Develop backend services and APIs using Python, FastAPI, Flask, or similar frameworks
• Design prompts, system instructions, and context-management strategies
• Build scalable AI services from prototypes into production
• Evaluate LLM outputs and improve quality, accuracy, latency, reliability, and cost
• Monitor, troubleshoot, and optimize deployed AI systems
• Implement evaluation, validation, guardrails, and error-handling strategies
• Identify and resolve production issues and system regressions
• Partner with engineering, product, operations, and business teams to translate requirements into practical AI solutions
• Contribute to architecture decisions, technical discussions, and documentation
• Stay current with Generative AI, LLMs, RAG, agentic AI, and emerging AI tooling
• Evaluate and implement new AI models, frameworks, and techniques
• Collaborate with engineering leadership, product teams, software engineers, backend developers, global AI research and development teams, and business stakeholders

• 3+ years of software engineering, AI/ML engineering, or related development experience
• Strong proficiency in Python
• Practical experience building applications using LLMs
• Hands-on experience with RAG, embeddings, semantic search, and vector databases
• Experience integrating LLM APIs such as OpenAI, Anthropic, Azure OpenAI, or similar platforms
• Understanding of prompt engineering, model behavior, context management, and LLM evaluation
• Experience developing APIs or backend services using FastAPI, Flask, or similar frameworks
• Strong software engineering fundamentals, including Git, REST APIs, testing, debugging, and system design
• Familiarity with Docker and modern development practices
• Ability to take an AI use case from requirements through development, testing, and deployment
• Strong problem-solving skills and written/verbal English communication
• Ability to work effectively in a fully remote, globally distributed team
• Experience building production AI copilots, chatbots, agents, or intelligent automation systems
• Experience with LangChain, LlamaIndex, LangGraph, or similar AI orchestration frameworks
• Experience with Pinecone, Weaviate, Qdrant, FAISS, Chroma, or similar vector databases
• Familiarity with agentic workflows, tool/function calling, and multi-step AI systems
• Experience with LLM fine-tuning, LoRA, or similar techniques
• Experience deploying AI applications in AWS, Azure, or GCP
• Familiarity with model monitoring, evaluation frameworks, guardrails, and responsible AI practices
• Experience with SQL, CI/CD, Kubernetes, or model-serving infrastructure
• Comfortable working Monday through Friday, 7:00 AM–4:00 PM Pacific Time, corresponding to overnight hours in India
• Ability to work occasional weekends or schedule adjustments when business needs require

• Contract and payment administration facilitated through Deel
• 90-day probationary period
• Benefits eligibility upon successful completion of probation
• Paid Time Off (PTO) in accordance with company policy
• Holiday pay for company-observed holidays
• Career growth and professional development opportunities