Job
Description
We are looking for a motivated and curious Generative AI Engineer (Junior to Mid-Level) to join our growing Generative AI team. In this role, you’ll work closely with senior engineers to help develop and deploy cutting-edge generative AI systems across real business use cases. You'll contribute to solutions that integrate large language models (LLMs), embeddings, vector databases, and GenAI development frameworks. This is a hands-on role that offers the opportunity to work with production-grade GenAI technologies, grow your skill set, and have a real impact on user-facing AI features. Role and Responsibilities Typical duties and responsibilities for Gen-AI engineer position may include but not limited to: Support the fine-tuning, deployment, and integration of large language models (LLMs) and other generative models (e.g., GPT, Mistral). Build and maintain retrieval-augmented generation (RAG) pipelines using embeddings and vector databases like FAISS, Pinecone, or Chroma. Contribute to prompt engineering, schema design, and function calling logic to guide LLM behavior in production workflows. Work with GenAI development frameworks to build, orchestrate, route, and serve GenAI-powered features, workflows, and agents. Stay up to date with the latest advancements in generative AI, prompt tooling, and language model APIs. Participate in experiments exploring new architectures, model capabilities, and prompting techniques. Help evaluate model behaviors and document findings to support continual improvement. Work under the guidance of senior AI engineers and participate in code reviews, design discussions, and technical planning. Take ownership of well-scoped components and contribute to production releases. Embrace a learning-first environment and help foster a collaborative, transparent team culture. Collaborate with cross-functional teams (engineering, product, design) to deliver user-facing GenAI features. Implement backend APIs and services powered by LLMs, including local and cloud-hosted models. Support LLM observability efforts to track pipelines’ execution, logs, LLM calls, performance, latency, and failure cases. Assist in evaluating and mitigating bias, hallucination, and safety risks in generative AI systems. Ensure that outputs and user-facing AI behavior follow responsible AI principles and privacy standards. Knowledge sharing and culture building as we work in team structure, it is very essential to have the spirit of sharing the knowledge. Keep aligned with our team(s) coding and design standards. Ability to communicate and work well with others. Ability to deliver on time keeping a high quality of work. To quickly become an expert in our tech stack, specifically the systems relating to your role. Requesting training when required. Check in with your line manager and update on your progress. Qualifications: Bachelor’s degree in Computer Science, Artificial Intelligence, Machine Learning, or a related field (or equivalent hands-on experience). 2+ years of experience in software development or applied machine learning (including internships, research, or open-source contributions). Proven hands-on experience working with LLM APIs Practical exposure to embeddings , vector databases , and RAG workflows. Experience using core frameworks such as LangChain , LangGraph , LiteLLM , or Ollama . Proficiency in Python and familiarity with AI/ML libraries such as Hugging Face Transformers or PyTorch. Understanding of prompt engineering, output parsing, and function/tool calling with LLMs. Familiarity with vector databases (e.g., FAISS, Pinecone, Weaviate, Chroma) and semantic retrieval techniques. Basic understanding of structured outputs using Pydantic or JSON schema. Experience with LLM observability tools like LangSmith , LangFuse , Opik , etc.. Comfortable working with Git, APIs, and cloud platforms (AWS, GCP, etc.) Experience building or contributing to agentic workflows, multi-step LLM tools, or stateful AI agents is a Plus. Awareness of ethical AI challenges, bias mitigation, and model evaluation techniques is a Plus. Contributions to open-source AI projects or technical writing in the GenAI space is a Plus. Strong analytical and problem-solving abilities. Excellent communication and collaboration skills across technical and non-technical teams. Excellent verbal and written English communication skills. High attention to detail, curiosity, and willingness to experiment and learn. Show more Show less
