Adaps
Website:
adaps.com
Job details:
Role Overview
We are seeking a skilled and proactive AI Developer to join our engineering team. In this role, you will be responsible for integrating large language models and AI capabilities into our product workflows ensuring models produce accurate, reliable, and contextually correct results. The ideal candidate has strong Python fundamentals, hands-on experience with LLM APIs and prompt engineering, and a deep understanding of how to make AI systems work reliably in production. This role focuses on applied AI integration rather than model training or research.
Responsibilities
• Integrate LLMs (OpenAI, Anthropic, open-source models, etc.) into product workflows via APIs
• Design, test, and iterate on prompts to consistently produce correct outputs for business use cases
• Build context engineering pipelines, retrieval, chunking, embeddings, and vector store integration (RAG)
• Implement output validation, guardrails, and structured output handling (JSON schemas, function calling)
• Develop evaluation frameworks and test harnesses to measure model accuracy and regressions
• Build agentic or multi-step workflows that combine LLMs with tools, APIs, and business logic
• Optimize for cost, latency, and token efficiency across model calls
• Handle exception management, logging, debugging, and production issue resolution for AI features
• Collaborate with backend, frontend, and product teams to embed AI capabilities into user-facing workflows
• Follow best practices in prompt versioning, observability, and responsible AI usage
Nice to Have
• Experience with frameworks like LangChain, LlamaIndex, or LangGraph
• Familiarity with vector databases (Pinecone, Weaviate, pgvector, Qdrant)
• Exposure to fine-tuning, embeddings, or model evaluation tools
• Experience with Docker, Kubernetes, CI/CD
• Familiarity with AWS / Azure / GCP AI services (Bedrock, Azure OpenAI, Vertex AI)
Click on Apply to know more.