We are looking for a highly experienced GenAI Engineer with deep expertise in prompt engineering, retrieval-augmented generation (RAG), and vector-based search systems to help integrate GenAI into our engineering and DevOps ecosystem.
As a contractor in this role, you will build intelligent, context-aware assistants and agents that augment CI/CD workflows, knowledge retrieval, incident handling, and developer productivity using LLMs, Python, and NLP pipelines. You will lead the charge in making our platform smarter and more autonomous by embedding GenAI natively into infrastructure and developer experience workflows.
Key Responsibilities:
- Design, iterate, and optimize prompts for task-specific LLM workflows with high accuracy, relevance, and controllability
- Build RAG pipelines using vector databases like FAISS, Weaviate, Pinecone, or similar to support knowledge retrieval and contextual AI agents
- Integrate LLMs into internal engineering tools, CI/CD workflows, and observability systems for real-time summarization, automation, and productivity enhancement
- Leverage Python-based frameworks like LangChain, LlamaIndex, Haystack, and others to implement end-to-end GenAI solutions
- Fine-tune open-source or commercial models (OpenAI, Claude, Cohere, Mistral, etc.) as needed for domain-specific use cases
- Collaborate with DevOps and platform teams to identify automation and GenAI augmentation opportunities
- Ensure data privacy, governance, and ethical standards are met when using internal datasets or embedding knowledge
- Optimize response quality through prompt chaining, feedback loops, and context compression techniques
- Experience integrating GenAI into CI/CD tools, observability dashboards, or chat-based interfaces
Required Skills & Experience:
- 610+ years in engineering roles with 2+ years hands-on in GenAI, NLP, or LLM-based systems
- Proven experience in prompt engineering and LLM integration for backend or infrastructure automation
- Strong Python development skills and working knowledge of LangChain, LlamaIndex, Hugging Face Transformers, or similar GenAI libraries
- Deep understanding of vector databases (e.g., FAISS, Pinecone, Weaviate, Qdrant) and embedding techniques
- Experience designing and deploying RAG architectures for internal knowledge access and contextually intelligent systems
- Familiarity with NLP concepts like tokenization, summarization, intent extraction, semantic similarity, etc.
- Experience with LLM APIs (OpenAI, Azure OpenAI, Claude, etc.) and streaming response generation
- Ability to work in fast-paced, iterative development cycles in a collaborative DevOps/platform engineering environment
Nice to Have:
- Understanding of multi-modal models or fine-tuning open LLMs for specialized use
- Familiarity with developer-facing GenAI use cases: changelog generation, log triage, infra as code review, chatbot copilots
- Experience working with Kubernetes, GitOps, or DevSecOps platforms
