GenAI Engineer
Qualifications
Experience Level: Mid Level
- </b></li><li>. <br /><br />Strong programming skills in Python
- with familiarity in modern ML tooling. <br /><br />Practical experience with LLM frameworks (e.g.
- Hugging Face Transformers
- LangChain
- LlamaIndex). <br /><br />Experience building or deploying RAG pipelines
- including handling embeddings and vector search. <br /><br />Understanding of transformer models
- prompt engineering
- and tokenization strategies. <br /><br />Hands-on with APIs (OpenAI
- Anthropic
- Cohere
Full Job Description
Soul AI is seeking a talented Generative AI Engineer to join one of our client's teams. In this role, you will be instrumental in building intelligent systems powered by cutting-edge large language models and other generative AI architectures. Your responsibilities will include developing and deploying LLM-based features, integrating vector search capabilities, fine-tuning models, and collaborating closely with product and engineering teams to deliver robust, scalable GenAI applications. You will have the opportunity to work across the entire GenAI stack, from prompt design to inference optimization, and significantly influence how generative models are utilized in real-world products.
Responsibilities:
- Fine-tune and deploy Large Language Models (LLMs) such as GPT, LLaMA, and Mistral, utilizing frameworks like Hugging Face Transformers or LangChain.
- Develop and optimize Retrieval-Augmented Generation (RAG) pipelines, integrating vector databases like Pinecone or FAISS.
- Engineer effective prompts to ensure structured and reliable outputs for various use cases, including chatbots, summarization, and coding copilots.
- Implement scalable inference pipelines and optimize for latency, throughput, and cost through techniques such as quantization or model distillation.
- Collaborate with product, design, and frontend teams to seamlessly integrate GenAI capabilities into user-facing features.
- Monitor, evaluate, and continuously improve model performance, safety, and accuracy in production environments.
- Ensure adherence to privacy, safety, and responsible AI practices, including content filtering and output sanitization.
Required Skills:
- Strong proficiency in Python programming, with a solid understanding of modern ML tooling.
- Practical experience with LLM frameworks such as Hugging Face Transformers, LangChain, or LlamaIndex.
- Proven experience in building or deploying RAG pipelines, including managing embeddings and vector search.
- Solid understanding of transformer models, prompt engineering techniques, and tokenization strategies.
- Hands-on experience with APIs from providers like OpenAI, Anthropic, and Cohere, and model serving frameworks such as FastAPI or Flask.
- Experience deploying ML models using Docker, Kubernetes, and/or cloud platforms (AWS, GCP, Azure).
- Comfort and experience with ML model evaluation, monitoring, and troubleshooting inference pipelines.
Nice to Have:
- Experience with multimodal models, including diffusion models, Text-to-Speech (TTS), and image/video generation.
- Knowledge of Reinforcement Learning from Human Feedback (RLHF), safety alignment, or best practices for model fine-tuning.
- Familiarity with open-source LLMs like Mistral, LLaMA, Falcon, and Mixtral, along with optimization techniques such as LoRA and quantization.
- Experience with LangChain agents, tool usage, and memory management.
- Contributions to open-source GenAI projects or published demos/blogs on generative AI topics.
- Exposure to frontend technologies like React/Next.js for prototyping GenAI tools.
Educational Qualifications:
Bachelor's or Master's degree in Computer Science, Artificial Intelligence, Machine Learning, Data Science, or a related technical field. Candidates with significant relevant project experience or open-source contributions will be considered, irrespective of formal degree attainment.
Company
Soul Ai
Soul AI, founded by esteemed alumni from IIT Bombay and IIM Ahmedabad, boasts a robust founding team with backgrounds from premier institutions like IITs, NITs, and BITS. We are at the forefront of de...