AI Engineer

Company Description

Tethr is a talent-centric organization built on the principle "For Talent. By Talent." and is dedicated to connecting Pakistani professionals to international clientele & creating impactful, modern digital products. The company focuses on empowering skilled professionals to build, grow, and innovate across diverse technology platforms. Team members collaborate in a supportive, remote-first environment that values autonomy, ownership, and continuous improvement.

Role Description

• Hands-on AI Engineer with strong software engineering fundamentals and real experience building modern AI applications using Large Language Models
• Designs and builds applications, agents, and agentic workflows capable of using tools, APIs, databases, and files
• Builds multi-step AI workflows involving orchestration, state, memory, retries, and failure handling
• Integrates models from providers such as OpenAI, Anthropic, Google, and Azure OpenAI
• Builds and improves Retrieval-Augmented Generation (RAG), semantic search, and knowledge-retrieval solutions
• Implements structured outputs, function/tool calling, model routing, and controlled AI execution
• Develops evaluation and testing processes for AI output quality, grounding, reliability, and cost
• Implements AI guardrails, monitoring, logging, and human-in-the-loop controls
• Integrates AI solutions with backend systems, APIs, and SQL databases while writing clean, modular, maintainable Python
• Creates and maintains clear technical documentation

Summary

The ideal candidate holds a bachelor's degree in Computer Science, Software Engineering, AI, Data Science, or a related field, with 2+ years of relevant experience in AI engineering, ML engineering, backend, or software engineering, and has built at least one meaningful LLM or Generative AI system beyond a basic chatbot or API demo. Strong Python proficiency is essential, along with hands-on experience with major LLM APIs, a practical understanding of AI agents (tool/function calling, context, state, orchestration), and experience with at least one orchestration framework such as LangGraph, LangChain, LlamaIndex, PydanticAI, or CrewAI. A working knowledge of RAG, embeddings, semantic search, and vector databases is expected, as is experience with REST APIs, JSON, SQL, Git, testing, Docker, and cloud-based development. Experience with Microsoft Azure/Fabric, LLM evaluation frameworks, AI observability and cost monitoring, Model Context Protocol (MCP), multi-agent systems, prompt-injection defenses, CI/CD, FastAPI, or vector databases like Pinecone, Qdrant, Weaviate, or Chroma is a strong plus. We're looking for people who've actually built AI systems rather than completed courses, who think like an engineer first, document their work clearly, challenge assumptions when it matters, and take ownership of what they build. Applicants should be ready to walk us through one substantial AI or LLM-based system they personally built end to end, the problem, the architecture, what they implemented, how they tested it, and what they'd improve. A GitHub profile, portfolio, or deployed project is strongly preferred.

Additional Details

• Salary Range: $850-$900
• Fully Remote
• Company Laptop will be provided
• US Timings - Eastern Standard Time