LLM / RAG Engineer
Primary stack
Nice to have's
Job description
About the Position
Overview
We are seeking an LLM / RAG Engineer to work on an enterprise knowledge assistant used by internal teams to search policies, product documentation, support articles, technical manuals, and operational knowledge bases. The system focuses on grounded answers, source attribution, document access rules, and measurable response quality.
Technologies
- Python 3.11+
- FastAPI
- LangChain / LlamaIndex
- Qdrant / pgvector
- embeddings
- hybrid search
- reranking
- OpenAI / Azure OpenAI
Responsibilities
- Design and implement RAG pipelines for structured and unstructured enterprise documents.
- Work on chunking strategies, metadata extraction, access-aware retrieval, hybrid search, and reranking.
- Integrate vector search with backend APIs and user-facing knowledge assistant workflows.
- Evaluate answer quality, retrieval quality, hallucination risk, latency, and cost.
- Build ingestion pipelines for PDFs, web pages, internal documents, and knowledge base content.
- Implement source citations, confidence indicators, guardrails, and fallback behaviors.
- Collaborate with product and domain teams to define evaluation scenarios and acceptance criteria.
Requirements
- 3+ years of commercial software engineering experience, with hands-on LLM/RAG project experience.
- Strong Python backend skills and experience with FastAPI or similar frameworks.
- Experience with vector databases such as Qdrant, pgvector, Pinecone, Weaviate, or Milvus.
- Understanding of embeddings, semantic search, hybrid search, reranking, chunking, and retrieval evaluation.
- Experience with OpenAI, Azure OpenAI, Anthropic, Gemini, or similar model providers.
- Ability to build production-quality systems with logging, monitoring, tests, and cost awareness.
- Strong spoken English - B2+ or higher for discussing retrieval quality and product trade-offs with international teams.
Nice to Have
- Experience with document parsing, OCR, layout-aware extraction, or metadata pipelines.
- Experience with LangSmith, Ragas, DeepEval, or custom RAG evaluation frameworks.
- Experience with permissions-aware enterprise search.
- Experience in legal tech, edtech, healthcare, enterprise SaaS, or internal knowledge management platforms.
Apply
If you enjoy building grounded LLM systems with measurable quality rather than generic chatbots, we would be glad to hear from you. Send us your CV and we will contact you to discuss relevant opportunities.
We Offer
- Remote / Hybrid work options
About the Company
We are committed to building innovative AI solutions that drive measurable results. Join our team and contribute to projects that make a real impact.
© Infinity Technologies. This job description was sourced from the employer's public career page. TheJob is not the employer — we index the posting and route candidates to the source. All content rights and hiring decisions belong to the employer.
Infinity Technologies, headquartered in London, specializes in creating global R&D hubs to help businesses achieve their goals. Promoting fully remote teams and a lean approach, we eliminate unnecessary office costs, sales, marketing expenses, and overheads for our customers. Our innovative fractal model ensures each R&D hub functions as a self-contained ecosystem tailored to the unique needs of each customer, acting as an extension of their team to develop products, maintain services, or execute strategic objectives.We leverage over 20 trademarked frameworks for building teams, developing software products, and designing outsourcing strategies, focusing on startups andmid-sizedcustomers. Our goal is to help them globalize their R&D efforts efficiently. Infinity Technologies also maintains a library of reusable components, enabling rapid prototyping, idea validation, and faster time to market—all while reducing costs. Since 2003, we have built 81 R&D hubs and currently operate 12 active hubs with distributed teams in 21 countries.With our expertise in cost-effective practices, economies of scale, and lean methodologies, Infinity Technologies empowers businesses to innovate, grow, and succeed in a global marketplace.